课程五(Sequence Models)，第一 周（Recurrent Neural Networks） —— 3.Programming assignments：Jazz improvisation with LSTM

Improvise a Jazz Solo with an LSTM Network

Welcome to your final programming assignment of this week! In this notebook, you will implement a model that uses an LSTM to generate music. You will even be able to listen to your own music at the end of the assignment.

You will learn to:

  • Apply an LSTM to music generation.
  • Generate your own jazz music with deep learning.

Please run the following cell to load all the packages required in this assignment. This may take a few minutes.

【code】

from __future__ import print_function
import IPython
import sys
from music21 import *
import numpy as np
from grammar import *
from qa import *
from preprocess import * 
from music_utils import *
from data_utils import *
from keras.models import load_model, Model
from keras.layers import Dense, Activation, Dropout, Input, LSTM, Reshape, Lambda, RepeatVector
from keras.initializers import glorot_uniform
from keras.utils import to_categorical
from keras.optimizers import Adam
from keras import backend as K

1 - Problem statement

You would like to create a jazz music piece specially for a friend's birthday. However, you don't know any instruments or music composition. Fortunately, you know deep learning and will solve this problem using an LSTM netwok.

You will train a network to generate novel jazz solos in a style representative of a body of performed work.

1.1 - Dataset

You will train your algorithm on a corpus of Jazz music. Run the cell below to listen to a snippet of the audio from the training set:

【code】

IPython.display.Audio('./data/30s_seq.mp3')

【result】

注：原文是一段音乐

　　

We have taken care of the preprocessing of the musical data to render it in terms of musical "values." You can informally think of each "value" as a note, which comprises a pitch and a duration. For example, if you press down a specific piano key for 0.5 seconds, then you have just played a note. In music theory, a "value" is actually more complicated than this--specifically, it also captures the information needed to play multiple notes at the same time. For example, when playing a music piece, you might press down two piano keys at the same time (playng multiple notes at the same time generates what's called a "chord"). But we don't need to worry about the details of music theory for this assignment. For the purpose of this assignment, all you need to know is that we will obtain a dataset of values, and will learn an RNN model to generate sequences of values.

Our music generation system will use 78 unique values. Run the following code to load the raw music data and preprocess it into values. This might take a few minutes.

　

 【中文翻译】

我们已经注意到音乐数据的预处理, 以音乐的 "value" 来呈现它。你可以非正式地把每个 "value" 看作音符, 包括音高和持续时间。例如, 如果你按下一个特定的钢琴键0.5 秒, 那么你刚才打了一个音符。在音乐理论中, "价value" 实际上比这更复杂--具体地说, 它还捕获了同时播放多个音符所需的信息。例如, 当播放音乐片断时, 您可能同时按下两个钢琴键 (生成多个音符同时生成所谓的 "和弦")。但我们不需要为这个任务的音乐理论的细节担心。对于此任务, 您需要知道的是, 我们将获得一个values的数据集, 并将学习一个 RNN 模型来生成values序列。
我们的音乐生成系统将使用78不一样的values。运行以下代码以加载原始音乐数据并将其预处理为values。这可能需要几分钟。

【code】

X, Y, n_values, indices_values = load_music_utils()
print('shape of X:', X.shape)
print('number of training examples:', X.shape[0])
print('Tx (length of sequence):', X.shape[1])
print('total # of unique values:', n_values)
print('Shape of Y:', Y.shape)

【result】

shape of X: (60, 30, 78)
number of training examples: 60
Tx (length of sequence): 30
total # of unique values: 78
Shape of Y: (30, 60, 78)

　　

You have just loaded the following:

  • X: This is an (m, Tx, 78) dimensional array. We have m training examples, each of which is a snippet of Tx=30 musical values. At each time step, the input is one of 78 different possible values, represented as a one-hot vector. Thus for example, X[i,t,:] is a one-hot vector representating the value of the i-th example at time t.

  • Y: This is essentially the same as X, but shifted one step to the left (to the past). Similar to the dinosaurus assignment, we're interested in the network using the previous values to predict the next value, so our sequence model will try to predict y⟨t⟩ given x⟨1⟩,…,x⟨t⟩ . However, the data in Y is reordered to be dimension (Ty,m,78), where Ty=Tx. This format makes it more convenient to feed to the LSTM later.

  • n_values: The number of unique values in this dataset. This should be 78.

  • indices_values: python dictionary mapping from 0-77 to musical values.

　　

1.2 - Overview of our model

Here is the architecture of the model we will use. This is similar to the Dinosaurus model you had used in the previous notebook, except that in you will be implementing it in Keras. The architecture is as follows:

We will be training the model on random snippets of 30 values taken from a much longer piece of music. Thus, we won't bother to set the first input x⟨1⟩=0⃗ , which we had done previously to denote the start of a dinosaur name, since now most of these snippets of audio start somewhere in the middle of a piece of music. We are setting each of the snippts to have the same length Tx=30 to make vectorization easier.

 【中文翻译】

 我们将用从一个更长的一段音乐随机选30个values的片段训练模型。因此, 我们不会费心设置第一个输入 x⟨1⟩=0⃗, 这是我们以前做的, 以表示恐龙名称的开始, 因为现在大部分的音频片段开始在音乐的中间某处。我们设置每个 snippts 具有相同的长度 Tx=30, 使矢量化更容易。

2 - Building the model

In this part you will build and train a model that will learn musical patterns. To do so, you will need to build a model that takes in X of shape (m,Tx,78) and Y of shape (Ty,m,78). We will use an LSTM with 64 dimensional hidden states. Lets set n_a = 64.

【code】

n_a = 64

Here's how you can create a Keras model with multiple inputs and outputs. If you're building an RNN where even at test time entire input sequence x⟨1⟩,x⟨2⟩,…,x⟨Tx⟩ were given in advance, for example if the inputs were words and the output was a label, then Keras has simple built-in functions to build the model. However, for sequence generation, at test time we don't know all the values of x⟨t⟩ in advance; instead we generate them one at a time using x⟨t⟩=y⟨t−1⟩. So the code will be a bit more complicated, and you'll need to implement your own for-loop to iterate over the different time steps.

The function djmodel() will call the LSTM layer Tx times using a for-loop, and it is important that all Tx copies have the same weights. I.e., it should not re-initiaiize the weights every time---the Tx steps should have shared weights. The key steps for implementing layers with shareable weights in Keras are:

  1. Define the layer objects (we will use global variables for this).
  2. Call these objects when propagating the input.

We have defined the layers objects you need as global variables. Please run the next cell to create them. Please check the Keras documentation to make sure you understand what these layers are: Reshape(), LSTM(), Dense().

【code】
reshapor = Reshape((1, 78))                        # Used in Step 2.B of djmodel(), below
LSTM_cell = LSTM(n_a, return_state = True)         # Used in Step 2.C
densor = Dense(n_values, activation='softmax')     # Used in Step 2.D

Each of reshapor, LSTM_cell and densor are now layer objects, and you can use them to implement djmodel(). In order to propagate a Keras tensor object X through one of these layers, use layer_object(X) (or layer_object([X,Y]) if it requires multiple inputs.). For example, reshapor(X) will propagate X through the Reshape((1,78)) layer defined above.　　

　　

【中文翻译】 

下面是如何创建具有多个输入和输出的 Keras 模型的方法。如果您正在构建一个 RNN, 即使在测试时整个输入序列x⟨1⟩,x⟨2⟩,…,x⟨Tx⟩是事先给出的, 例如, 如果输入是单词, 输出是一个标签, 那么 Keras 有简单的内置函数来构建模型。然而, 对于序列生成, 在测试时, 我们不能提前知道所有的 x⟨t⟩值;相反, 我们使用 x⟨t⟩=y⟨t−1⟩一次生成一个。因此, 代码将变得更加复杂, 您需要实现自己的 for 循环来循环访问不同的时间步。
函数 djmodel () 将使用 for 循环调用 LSTM 层 TxT次, 并且所有 Tx  副本具有相同的权重非常重要。也就是说, 每次---第Tx步都应该有共享权重时, 它不应该重新初始化权重。在 Keras 中实现具有共享权重的层的关键步骤是:
  1. 定义层对象 (我们将为此使用全局变量)。
  2. 前向传播输入时调用这些对象。
我们已将需要的层对象定义为全局变量。请运行下一个单元格以创建它们。请检查 Keras 文档, 以确保您了解这些层是什么: Reshape(), LSTM(), Dense().
【code】
reshapor = Reshape((1, 78))                        # Used in Step 2.B of djmodel(), below
LSTM_cell = LSTM(n_a, return_state = True)         # Used in Step 2.C
densor = Dense(n_values, activation='softmax')     # Used in Step 2.D
reshapor、LSTM_cell 和 densor 现在都是层对象, 您可以使用它们来实现 djmodel ()。为了将 Keras 张量对象 X 通过这些层之一传播, 请使用 layer_object (x) (或 layer_object ([x, Y]), 如果它需要多个输入。例如, reshapor (x) 将通过上面定义的 Reshape((1,78)) 传播 X。
 
 

Exercise: Implement djmodel(). You will need to carry out 2 steps:

  1. Create an empty list "outputs" to save the outputs of the LSTM Cell at every time step.

  2. Loop for t∈1,…,Tx:

    A. Select the "t"th time-step vector from X. The shape of this selection should be (78,). To do so, create a custom Lambda layer in Keras by using this line of code:

            x = Lambda(lambda x: X[:,t,:])(X)

    Look over the Keras documentation to figure out what this does. It is creating a "temporary" or "unnamed" function (that's what Lambda functions are) that extracts out the appropriate one-hot vector, and making this function a Keras Layer object to apply to X.

    B. Reshape x to be (1,78). You may find the reshapor() layer (defined below) helpful.

    C. Run x through one step of LSTM_cell. Remember to initialize the LSTM_cell with the previous step's hidden state a and cell state c. Use the following formatting:

    a, _, c = LSTM_cell(input_x, initial_state=[previous hidden state, previous cell state])

    D. Propagate the LSTM's output activation value through a dense+softmax layer using densor.

    E. Append the predicted value to the list of "outputs"

【中文翻译】
练习: 实现 djmodel ()。您将需要执行2步:
1、创建一个空列表 "输出" 以在每步骤中保存 LSTM 单元格的输出。
2、t∈1,..., Tx的循环:
　　a. 从 x 中选择 "t" 时间步的向量。此选择的形状应为 (78，)。为此, 请使用以下代码行在 Keras 中创建自定义 Lambda 层:
　　　          x = Lambda(lambda x: X[:,t,:])(X)
　　查看 Keras 文档, 找出这是什么。它正在创建一个 "临时" 或 "未命名" 函数 (这就是 Lambda 函数), 它提取出适当的one-hot 向量, 并使这个函数成为一个 Keras 层对象，应用于 x。
　　b. 重塑 x 为 (1，78)。您可能会发现 reshapor () 层 (定义如下) 很有用。
　　c. 通过 LSTM_cell 的一步运行 x。请记住, 使用上一步的隐藏状态 a 和单元格状态 c初始化 LSTM_cell. 请使用以下格式:　　　
　　　　　　a, _, c = LSTM_cell(input_x, initial_state=[previous hidden state, previous cell state])
d. 使用 densor 将 LSTM 的输出激活值通过dense+softma 层传播。
e. 将预测值追加到 "outputs" 列表中
 
【code】
  
# GRADED FUNCTION: djmodel

def djmodel(Tx, n_a, n_values):
    """
    Implement the model
    
    Arguments:
    Tx -- length of the sequence in a corpus
    n_a -- the number of activations used in our model
    n_values -- number of unique values in the music data 
    
    Returns:
    model -- a keras model with the 
    """
    
    # Define the input of your model with a shape 
    X = Input(shape=(Tx, n_values))
    
    # Define s0, initial hidden state for the decoder LSTM
    a0 = Input(shape=(n_a,), name='a0')
    c0 = Input(shape=(n_a,), name='c0')
    a = a0
    c = c0
    
    ### START CODE HERE ### 
    # Step 1: Create empty list to append the outputs while you iterate (≈1 line)
    outputs =[]
    
    # Step 2: Loop
    for t in range(Tx):
        
        # Step 2.A: select the "t"th time step vector from X. 
        x = Lambda(lambda x: X[:,t,:])(X)
        # Step 2.B: Use reshapor to reshape x to be (1, n_values) (≈1 line)
        x = reshapor(x)
        # Step 2.C: Perform one step of the LSTM_cell
        a, _, c =LSTM_cell(x, initial_state=[a, c])
        # Step 2.D: Apply densor to the hidden state output of LSTM_Cell
        out = densor(a)
        # Step 2.E: add the output to "outputs"
        outputs.append(out)
        
    # Step 3: Create model instance
    model = Model([X, a0, c0], outputs)
    
    ### END CODE HERE ###
    
    return model

Run the following cell to define your model. We will use Tx=30, n_a=64 (the dimension of the LSTM activations), and n_values=78. This cell may take a few seconds to run.　　

 【code】
model = djmodel(Tx = 30 , n_a = 64, n_values = 78)

You now need to compile your model to be trained. We will Adam and a categorical cross-entropy loss.　　

【code】
opt = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, decay=0.01)

model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])

Finally, lets initialize a0 and c0 for the LSTM's initial state to be zero.　　

 【code】
m = 60
a0 = np.zeros((m, n_a))
c0 = np.zeros((m, n_a))

Lets now fit the model! We will turn Y to a list before doing so, since the cost function expects Y to be provided in this format (one list item per time-step). So list(Y) is a list with 30 items, where each of the list items is of shape (60,78). Lets train for 100 epochs. This will take a few minutes.　　

【code】
model.fit([X, a0, c0], list(Y), epochs=100)

【result】

60/60 [==============================] - 10s - loss: 125.8529 - dense_1_loss_1: 4.3551 - dense_1_loss_2: 4.3493 - dense_1_loss_3: 4.3470 - dense_1_loss_4: 4.3398 - dense_1_loss_5: 4.3465 - dense_1_loss_6: 4.3363 - dense_1_loss_7: 4.3419 - dense_1_loss_8: 4.3361 - dense_1_loss_9: 4.3341 - dense_1_loss_10: 4.3367 - dense_1_loss_11: 4.3352 - dense_1_loss_12: 4.3364 - dense_1_loss_13: 4.3334 - dense_1_loss_14: 4.3406 - dense_1_loss_15: 4.3430 - dense_1_loss_16: 4.3404 - dense_1_loss_17: 4.3394 - dense_1_loss_18: 4.3385 - dense_1_loss_19: 4.3373 - dense_1_loss_20: 4.3482 - dense_1_loss_21: 4.3504 - dense_1_loss_22: 4.3321 - dense_1_loss_23: 4.3359 - dense_1_loss_24: 4.3362 - dense_1_loss_25: 4.3372 - dense_1_loss_26: 4.3300 - dense_1_loss_27: 4.3367 - dense_1_loss_28: 4.3432 - dense_1_loss_29: 4.3361 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0500 - dense_1_acc_2: 0.0167 - dense_1_acc_3: 0.0500 - dense_1_acc_4: 0.0333 - dense_1_acc_5: 0.0500 - dense_1_acc_6: 0.0667 - dense_1_acc_7: 0.0167 - dense_1_acc_8: 0.0667 - dense_1_acc_9: 0.0833 - dense_1_acc_10: 0.0833 - dense_1_acc_11: 0.1000 - dense_1_acc_12: 0.0667 - dense_1_acc_13: 0.1000 - dense_1_acc_14: 0.1000 - dense_1_acc_15: 0.0667 - dense_1_acc_16: 0.0500 - dense_1_acc_17: 0.0500 - dense_1_acc_18: 0.0333 - dense_1_acc_19: 0.0833 - dense_1_acc_20: 0.0333 - dense_1_acc_21: 0.0333 - dense_1_acc_22: 0.0833 - dense_1_acc_23: 0.0667 - dense_1_acc_24: 0.0333 - dense_1_acc_25: 0.0833 - dense_1_acc_26: 0.0833 - dense_1_acc_27: 0.0500 - dense_1_acc_28: 0.0000e+00 - dense_1_acc_29: 0.0500 - dense_1_acc_30: 0.0667                                                                            
Epoch 2/100
60/60 [==============================] - 0s - loss: 122.7544 - dense_1_loss_1: 4.3347 - dense_1_loss_2: 4.3094 - dense_1_loss_3: 4.2825 - dense_1_loss_4: 4.2773 - dense_1_loss_5: 4.2667 - dense_1_loss_6: 4.2590 - dense_1_loss_7: 4.2565 - dense_1_loss_8: 4.2300 - dense_1_loss_9: 4.2312 - dense_1_loss_10: 4.2233 - dense_1_loss_11: 4.2101 - dense_1_loss_12: 4.2468 - dense_1_loss_13: 4.2106 - dense_1_loss_14: 4.2209 - dense_1_loss_15: 4.2269 - dense_1_loss_16: 4.2062 - dense_1_loss_17: 4.2054 - dense_1_loss_18: 4.2364 - dense_1_loss_19: 4.1858 - dense_1_loss_20: 4.2235 - dense_1_loss_21: 4.2506 - dense_1_loss_22: 4.2041 - dense_1_loss_23: 4.2150 - dense_1_loss_24: 4.2180 - dense_1_loss_25: 4.2309 - dense_1_loss_26: 4.1590 - dense_1_loss_27: 4.1974 - dense_1_loss_28: 4.2154 - dense_1_loss_29: 4.2209 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1500 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2000 - dense_1_acc_6: 0.1833 - dense_1_acc_7: 0.1667 - dense_1_acc_8: 0.2333 - dense_1_acc_9: 0.3167 - dense_1_acc_10: 0.1833 - dense_1_acc_11: 0.2833 - dense_1_acc_12: 0.1667 - dense_1_acc_13: 0.2167 - dense_1_acc_14: 0.2333 - dense_1_acc_15: 0.1833 - dense_1_acc_16: 0.1667 - dense_1_acc_17: 0.2000 - dense_1_acc_18: 0.1000 - dense_1_acc_19: 0.2333 - dense_1_acc_20: 0.1667 - dense_1_acc_21: 0.1333 - dense_1_acc_22: 0.2167 - dense_1_acc_23: 0.1333 - dense_1_acc_24: 0.1167 - dense_1_acc_25: 0.1833 - dense_1_acc_26: 0.2667 - dense_1_acc_27: 0.1000 - dense_1_acc_28: 0.1667 - dense_1_acc_29: 0.1500 - dense_1_acc_30: 0.0000e+00     
Epoch 3/100
60/60 [==============================] - 0s - loss: 116.2255 - dense_1_loss_1: 4.3127 - dense_1_loss_2: 4.2599 - dense_1_loss_3: 4.1974 - dense_1_loss_4: 4.1784 - dense_1_loss_5: 4.1434 - dense_1_loss_6: 4.1340 - dense_1_loss_7: 4.0999 - dense_1_loss_8: 4.0178 - dense_1_loss_9: 3.9695 - dense_1_loss_10: 3.9114 - dense_1_loss_11: 3.8346 - dense_1_loss_12: 4.0430 - dense_1_loss_13: 3.8753 - dense_1_loss_14: 3.9406 - dense_1_loss_15: 4.0071 - dense_1_loss_16: 3.8822 - dense_1_loss_17: 3.9446 - dense_1_loss_18: 4.1410 - dense_1_loss_19: 3.8155 - dense_1_loss_20: 3.9783 - dense_1_loss_21: 4.1062 - dense_1_loss_22: 3.9401 - dense_1_loss_23: 3.8582 - dense_1_loss_24: 3.9336 - dense_1_loss_25: 4.1589 - dense_1_loss_26: 3.6579 - dense_1_loss_27: 3.8531 - dense_1_loss_28: 3.9472 - dense_1_loss_29: 4.0836 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1833 - dense_1_acc_3: 0.2333 - dense_1_acc_4: 0.2167 - dense_1_acc_5: 0.2500 - dense_1_acc_6: 0.1833 - dense_1_acc_7: 0.1667 - dense_1_acc_8: 0.1833 - dense_1_acc_9: 0.2000 - dense_1_acc_10: 0.1833 - dense_1_acc_11: 0.1500 - dense_1_acc_12: 0.0667 - dense_1_acc_13: 0.1333 - dense_1_acc_14: 0.1500 - dense_1_acc_15: 0.0833 - dense_1_acc_16: 0.1000 - dense_1_acc_17: 0.1667 - dense_1_acc_18: 0.0333 - dense_1_acc_19: 0.1000 - dense_1_acc_20: 0.1000 - dense_1_acc_21: 0.0667 - dense_1_acc_22: 0.0500 - dense_1_acc_23: 0.0833 - dense_1_acc_24: 0.1000 - dense_1_acc_25: 0.0333 - dense_1_acc_26: 0.1333 - dense_1_acc_27: 0.0500 - dense_1_acc_28: 0.0833 - dense_1_acc_29: 0.0500 - dense_1_acc_30: 0.0000e+00         
Epoch 4/100
60/60 [==============================] - 0s - loss: 112.3930 - dense_1_loss_1: 4.2891 - dense_1_loss_2: 4.2088 - dense_1_loss_3: 4.0961 - dense_1_loss_4: 4.0642 - dense_1_loss_5: 3.9744 - dense_1_loss_6: 3.9618 - dense_1_loss_7: 3.9154 - dense_1_loss_8: 3.6984 - dense_1_loss_9: 3.7837 - dense_1_loss_10: 3.6319 - dense_1_loss_11: 3.6917 - dense_1_loss_12: 4.0104 - dense_1_loss_13: 3.7423 - dense_1_loss_14: 3.7658 - dense_1_loss_15: 3.7981 - dense_1_loss_16: 3.7433 - dense_1_loss_17: 3.8396 - dense_1_loss_18: 3.8980 - dense_1_loss_19: 3.6870 - dense_1_loss_20: 3.9754 - dense_1_loss_21: 4.0120 - dense_1_loss_22: 3.8370 - dense_1_loss_23: 3.7425 - dense_1_loss_24: 3.7522 - dense_1_loss_25: 4.0552 - dense_1_loss_26: 3.6071 - dense_1_loss_27: 3.7255 - dense_1_loss_28: 3.8845 - dense_1_loss_29: 4.0017 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1500 - dense_1_acc_3: 0.2167 - dense_1_acc_4: 0.1833 - dense_1_acc_5: 0.2333 - dense_1_acc_6: 0.1333 - dense_1_acc_7: 0.1333 - dense_1_acc_8: 0.2000 - dense_1_acc_9: 0.1167 - dense_1_acc_10: 0.1500 - dense_1_acc_11: 0.1333 - dense_1_acc_12: 0.0833 - dense_1_acc_13: 0.1167 - dense_1_acc_14: 0.1167 - dense_1_acc_15: 0.1000 - dense_1_acc_16: 0.1000 - dense_1_acc_17: 0.1500 - dense_1_acc_18: 0.1000 - dense_1_acc_19: 0.1000 - dense_1_acc_20: 0.0667 - dense_1_acc_21: 0.0667 - dense_1_acc_22: 0.1000 - dense_1_acc_23: 0.1333 - dense_1_acc_24: 0.0500 - dense_1_acc_25: 0.0333 - dense_1_acc_26: 0.1167 - dense_1_acc_27: 0.1000 - dense_1_acc_28: 0.0500 - dense_1_acc_29: 0.0167 - dense_1_acc_30: 0.0000e+00         
Epoch 5/100
60/60 [==============================] - 0s - loss: 109.5595 - dense_1_loss_1: 4.2718 - dense_1_loss_2: 4.1656 - dense_1_loss_3: 4.0210 - dense_1_loss_4: 3.9890 - dense_1_loss_5: 3.8568 - dense_1_loss_6: 3.8738 - dense_1_loss_7: 3.8611 - dense_1_loss_8: 3.6189 - dense_1_loss_9: 3.7345 - dense_1_loss_10: 3.5377 - dense_1_loss_11: 3.6354 - dense_1_loss_12: 3.9125 - dense_1_loss_13: 3.6405 - dense_1_loss_14: 3.6279 - dense_1_loss_15: 3.6873 - dense_1_loss_16: 3.6547 - dense_1_loss_17: 3.7806 - dense_1_loss_18: 3.7521 - dense_1_loss_19: 3.6108 - dense_1_loss_20: 3.8637 - dense_1_loss_21: 3.7914 - dense_1_loss_22: 3.6359 - dense_1_loss_23: 3.6119 - dense_1_loss_24: 3.6902 - dense_1_loss_25: 3.9219 - dense_1_loss_26: 3.5391 - dense_1_loss_27: 3.5776 - dense_1_loss_28: 3.7646 - dense_1_loss_29: 3.9310 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1333 - dense_1_acc_7: 0.1167 - dense_1_acc_8: 0.2333 - dense_1_acc_9: 0.1833 - dense_1_acc_10: 0.1000 - dense_1_acc_11: 0.1167 - dense_1_acc_12: 0.0667 - dense_1_acc_13: 0.1500 - dense_1_acc_14: 0.1500 - dense_1_acc_15: 0.1167 - dense_1_acc_16: 0.1167 - dense_1_acc_17: 0.1000 - dense_1_acc_18: 0.1000 - dense_1_acc_19: 0.1333 - dense_1_acc_20: 0.0667 - dense_1_acc_21: 0.1000 - dense_1_acc_22: 0.1333 - dense_1_acc_23: 0.1167 - dense_1_acc_24: 0.0833 - dense_1_acc_25: 0.0667 - dense_1_acc_26: 0.1167 - dense_1_acc_27: 0.1333 - dense_1_acc_28: 0.0833 - dense_1_acc_29: 0.0000e+00 - dense_1_acc_30: 0.0000e+00     
Epoch 6/100
60/60 [==============================] - 0s - loss: 107.7827 - dense_1_loss_1: 4.2563 - dense_1_loss_2: 4.1294 - dense_1_loss_3: 3.9500 - dense_1_loss_4: 3.9264 - dense_1_loss_5: 3.7709 - dense_1_loss_6: 3.8095 - dense_1_loss_7: 3.7957 - dense_1_loss_8: 3.5558 - dense_1_loss_9: 3.6318 - dense_1_loss_10: 3.4288 - dense_1_loss_11: 3.6222 - dense_1_loss_12: 3.8122 - dense_1_loss_13: 3.6177 - dense_1_loss_14: 3.6017 - dense_1_loss_15: 3.5962 - dense_1_loss_16: 3.6341 - dense_1_loss_17: 3.6278 - dense_1_loss_18: 3.7175 - dense_1_loss_19: 3.6283 - dense_1_loss_20: 3.7406 - dense_1_loss_21: 3.7675 - dense_1_loss_22: 3.6385 - dense_1_loss_23: 3.5488 - dense_1_loss_24: 3.5911 - dense_1_loss_25: 3.8451 - dense_1_loss_26: 3.4525 - dense_1_loss_27: 3.6568 - dense_1_loss_28: 3.6446 - dense_1_loss_29: 3.7849 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1333 - dense_1_acc_7: 0.1333 - dense_1_acc_8: 0.2833 - dense_1_acc_9: 0.2167 - dense_1_acc_10: 0.1500 - dense_1_acc_11: 0.1333 - dense_1_acc_12: 0.0833 - dense_1_acc_13: 0.1333 - dense_1_acc_14: 0.1500 - dense_1_acc_15: 0.1000 - dense_1_acc_16: 0.1500 - dense_1_acc_17: 0.2167 - dense_1_acc_18: 0.1000 - dense_1_acc_19: 0.1500 - dense_1_acc_20: 0.1333 - dense_1_acc_21: 0.1000 - dense_1_acc_22: 0.0667 - dense_1_acc_23: 0.1000 - dense_1_acc_24: 0.1167 - dense_1_acc_25: 0.0500 - dense_1_acc_26: 0.1500 - dense_1_acc_27: 0.0667 - dense_1_acc_28: 0.2000 - dense_1_acc_29: 0.1000 - dense_1_acc_30: 0.0000e+00         
Epoch 7/100
60/60 [==============================] - 0s - loss: 104.6787 - dense_1_loss_1: 4.2433 - dense_1_loss_2: 4.1005 - dense_1_loss_3: 3.8886 - dense_1_loss_4: 3.8610 - dense_1_loss_5: 3.6871 - dense_1_loss_6: 3.7653 - dense_1_loss_7: 3.7204 - dense_1_loss_8: 3.4254 - dense_1_loss_9: 3.5466 - dense_1_loss_10: 3.3470 - dense_1_loss_11: 3.4650 - dense_1_loss_12: 3.6976 - dense_1_loss_13: 3.4628 - dense_1_loss_14: 3.3877 - dense_1_loss_15: 3.4413 - dense_1_loss_16: 3.6093 - dense_1_loss_17: 3.5698 - dense_1_loss_18: 3.6047 - dense_1_loss_19: 3.4539 - dense_1_loss_20: 3.5784 - dense_1_loss_21: 3.6361 - dense_1_loss_22: 3.4370 - dense_1_loss_23: 3.4458 - dense_1_loss_24: 3.5320 - dense_1_loss_25: 3.6546 - dense_1_loss_26: 3.3850 - dense_1_loss_27: 3.5236 - dense_1_loss_28: 3.5430 - dense_1_loss_29: 3.6657 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.1833 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1167 - dense_1_acc_7: 0.1333 - dense_1_acc_8: 0.2667 - dense_1_acc_9: 0.1833 - dense_1_acc_10: 0.1833 - dense_1_acc_11: 0.1833 - dense_1_acc_12: 0.1333 - dense_1_acc_13: 0.2500 - dense_1_acc_14: 0.2667 - dense_1_acc_15: 0.1667 - dense_1_acc_16: 0.1500 - dense_1_acc_17: 0.2000 - dense_1_acc_18: 0.1833 - dense_1_acc_19: 0.1833 - dense_1_acc_20: 0.0833 - dense_1_acc_21: 0.1333 - dense_1_acc_22: 0.2000 - dense_1_acc_23: 0.1500 - dense_1_acc_24: 0.1333 - dense_1_acc_25: 0.1167 - dense_1_acc_26: 0.2333 - dense_1_acc_27: 0.1333 - dense_1_acc_28: 0.1500 - dense_1_acc_29: 0.1667 - dense_1_acc_30: 0.0000e+00     
Epoch 8/100
60/60 [==============================] - 0s - loss: 101.8910 - dense_1_loss_1: 4.2306 - dense_1_loss_2: 4.0669 - dense_1_loss_3: 3.8221 - dense_1_loss_4: 3.7882 - dense_1_loss_5: 3.6012 - dense_1_loss_6: 3.6790 - dense_1_loss_7: 3.6138 - dense_1_loss_8: 3.3292 - dense_1_loss_9: 3.4109 - dense_1_loss_10: 3.1760 - dense_1_loss_11: 3.4111 - dense_1_loss_12: 3.5720 - dense_1_loss_13: 3.3008 - dense_1_loss_14: 3.3247 - dense_1_loss_15: 3.3382 - dense_1_loss_16: 3.4691 - dense_1_loss_17: 3.3427 - dense_1_loss_18: 3.5503 - dense_1_loss_19: 3.2979 - dense_1_loss_20: 3.4666 - dense_1_loss_21: 3.5111 - dense_1_loss_22: 3.3364 - dense_1_loss_23: 3.3598 - dense_1_loss_24: 3.4490 - dense_1_loss_25: 3.6183 - dense_1_loss_26: 3.2521 - dense_1_loss_27: 3.4742 - dense_1_loss_28: 3.4564 - dense_1_loss_29: 3.6422 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.2167 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1333 - dense_1_acc_7: 0.1500 - dense_1_acc_8: 0.3000 - dense_1_acc_9: 0.2333 - dense_1_acc_10: 0.1667 - dense_1_acc_11: 0.1500 - dense_1_acc_12: 0.0667 - dense_1_acc_13: 0.2000 - dense_1_acc_14: 0.1833 - dense_1_acc_15: 0.1833 - dense_1_acc_16: 0.1667 - dense_1_acc_17: 0.2167 - dense_1_acc_18: 0.1500 - dense_1_acc_19: 0.2000 - dense_1_acc_20: 0.1333 - dense_1_acc_21: 0.1333 - dense_1_acc_22: 0.1833 - dense_1_acc_23: 0.1500 - dense_1_acc_24: 0.1333 - dense_1_acc_25: 0.1000 - dense_1_acc_26: 0.1667 - dense_1_acc_27: 0.1000 - dense_1_acc_28: 0.2000 - dense_1_acc_29: 0.0833 - dense_1_acc_30: 0.0000e+00         
Epoch 9/100
60/60 [==============================] - 0s - loss: 97.9816 - dense_1_loss_1: 4.2205 - dense_1_loss_2: 4.0356 - dense_1_loss_3: 3.7566 - dense_1_loss_4: 3.7172 - dense_1_loss_5: 3.5105 - dense_1_loss_6: 3.5887 - dense_1_loss_7: 3.5167 - dense_1_loss_8: 3.1895 - dense_1_loss_9: 3.2882 - dense_1_loss_10: 3.0166 - dense_1_loss_11: 3.2890 - dense_1_loss_12: 3.4061 - dense_1_loss_13: 3.1675 - dense_1_loss_14: 3.2013 - dense_1_loss_15: 3.1635 - dense_1_loss_16: 3.3460 - dense_1_loss_17: 3.2636 - dense_1_loss_18: 3.3513 - dense_1_loss_19: 3.1345 - dense_1_loss_20: 3.3233 - dense_1_loss_21: 3.2970 - dense_1_loss_22: 3.0926 - dense_1_loss_23: 3.3044 - dense_1_loss_24: 3.3985 - dense_1_loss_25: 3.4647 - dense_1_loss_26: 2.9930 - dense_1_loss_27: 3.2881 - dense_1_loss_28: 3.2028 - dense_1_loss_29: 3.4542 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.1833 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1333 - dense_1_acc_7: 0.1333 - dense_1_acc_8: 0.1500 - dense_1_acc_9: 0.1833 - dense_1_acc_10: 0.1500 - dense_1_acc_11: 0.1667 - dense_1_acc_12: 0.1167 - dense_1_acc_13: 0.1833 - dense_1_acc_14: 0.2500 - dense_1_acc_15: 0.2167 - dense_1_acc_16: 0.2167 - dense_1_acc_17: 0.2000 - dense_1_acc_18: 0.1500 - dense_1_acc_19: 0.3167 - dense_1_acc_20: 0.2500 - dense_1_acc_21: 0.1333 - dense_1_acc_22: 0.2667 - dense_1_acc_23: 0.2000 - dense_1_acc_24: 0.1333 - dense_1_acc_25: 0.1833 - dense_1_acc_26: 0.3500 - dense_1_acc_27: 0.1667 - dense_1_acc_28: 0.2000 - dense_1_acc_29: 0.1833 - dense_1_acc_30: 0.0000e+00     
Epoch 10/100
60/60 [==============================] - 0s - loss: 94.6552 - dense_1_loss_1: 4.2116 - dense_1_loss_2: 4.0041 - dense_1_loss_3: 3.7045 - dense_1_loss_4: 3.6346 - dense_1_loss_5: 3.4229 - dense_1_loss_6: 3.4832 - dense_1_loss_7: 3.4088 - dense_1_loss_8: 3.0882 - dense_1_loss_9: 3.1511 - dense_1_loss_10: 2.9165 - dense_1_loss_11: 3.1665 - dense_1_loss_12: 3.2547 - dense_1_loss_13: 3.0046 - dense_1_loss_14: 3.0086 - dense_1_loss_15: 3.0432 - dense_1_loss_16: 3.2060 - dense_1_loss_17: 3.0991 - dense_1_loss_18: 3.2141 - dense_1_loss_19: 3.0350 - dense_1_loss_20: 3.1686 - dense_1_loss_21: 3.2443 - dense_1_loss_22: 2.9960 - dense_1_loss_23: 3.2276 - dense_1_loss_24: 3.3056 - dense_1_loss_25: 3.2873 - dense_1_loss_26: 2.8111 - dense_1_loss_27: 3.1682 - dense_1_loss_28: 3.1132 - dense_1_loss_29: 3.2759 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.1833 - dense_1_acc_4: 0.1833 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1500 - dense_1_acc_7: 0.1167 - dense_1_acc_8: 0.1667 - dense_1_acc_9: 0.2000 - dense_1_acc_10: 0.1500 - dense_1_acc_11: 0.1833 - dense_1_acc_12: 0.1500 - dense_1_acc_13: 0.2833 - dense_1_acc_14: 0.2500 - dense_1_acc_15: 0.2167 - dense_1_acc_16: 0.2000 - dense_1_acc_17: 0.2500 - dense_1_acc_18: 0.1333 - dense_1_acc_19: 0.2667 - dense_1_acc_20: 0.2500 - dense_1_acc_21: 0.1000 - dense_1_acc_22: 0.2167 - dense_1_acc_23: 0.1333 - dense_1_acc_24: 0.1500 - dense_1_acc_25: 0.1333 - dense_1_acc_26: 0.3667 - dense_1_acc_27: 0.1333 - dense_1_acc_28: 0.2333 - dense_1_acc_29: 0.1167 - dense_1_acc_30: 0.0000e+00     
Epoch 11/100
60/60 [==============================] - 0s - loss: 90.8870 - dense_1_loss_1: 4.2033 - dense_1_loss_2: 3.9754 - dense_1_loss_3: 3.6613 - dense_1_loss_4: 3.5607 - dense_1_loss_5: 3.3416 - dense_1_loss_6: 3.3596 - dense_1_loss_7: 3.2801 - dense_1_loss_8: 2.9918 - dense_1_loss_9: 2.9926 - dense_1_loss_10: 2.8316 - dense_1_loss_11: 3.0280 - dense_1_loss_12: 3.0961 - dense_1_loss_13: 2.8310 - dense_1_loss_14: 2.9042 - dense_1_loss_15: 2.9165 - dense_1_loss_16: 3.1027 - dense_1_loss_17: 2.9343 - dense_1_loss_18: 3.0723 - dense_1_loss_19: 2.9344 - dense_1_loss_20: 3.0040 - dense_1_loss_21: 3.0750 - dense_1_loss_22: 2.8498 - dense_1_loss_23: 3.0615 - dense_1_loss_24: 3.0962 - dense_1_loss_25: 3.2058 - dense_1_loss_26: 2.6987 - dense_1_loss_27: 2.9898 - dense_1_loss_28: 2.8838 - dense_1_loss_29: 3.0049 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1000 - dense_1_acc_3: 0.2000 - dense_1_acc_4: 0.1833 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1667 - dense_1_acc_7: 0.1333 - dense_1_acc_8: 0.1833 - dense_1_acc_9: 0.2500 - dense_1_acc_10: 0.1667 - dense_1_acc_11: 0.1667 - dense_1_acc_12: 0.1333 - dense_1_acc_13: 0.2667 - dense_1_acc_14: 0.2667 - dense_1_acc_15: 0.1667 - dense_1_acc_16: 0.1833 - dense_1_acc_17: 0.2500 - dense_1_acc_18: 0.1500 - dense_1_acc_19: 0.2500 - dense_1_acc_20: 0.2333 - dense_1_acc_21: 0.1333 - dense_1_acc_22: 0.1833 - dense_1_acc_23: 0.1500 - dense_1_acc_24: 0.1833 - dense_1_acc_25: 0.1000 - dense_1_acc_26: 0.3000 - dense_1_acc_27: 0.2000 - dense_1_acc_28: 0.3000 - dense_1_acc_29: 0.1500 - dense_1_acc_30: 0.0167         
Epoch 12/100
60/60 [==============================] - 0s - loss: 87.5145 - dense_1_loss_1: 4.1959 - dense_1_loss_2: 3.9465 - dense_1_loss_3: 3.6126 - dense_1_loss_4: 3.4724 - dense_1_loss_5: 3.2535 - dense_1_loss_6: 3.2507 - dense_1_loss_7: 3.1489 - dense_1_loss_8: 2.8744 - dense_1_loss_9: 2.8876 - dense_1_loss_10: 2.7605 - dense_1_loss_11: 2.9153 - dense_1_loss_12: 2.9498 - dense_1_loss_13: 2.7008 - dense_1_loss_14: 2.7410 - dense_1_loss_15: 2.8283 - dense_1_loss_16: 2.9763 - dense_1_loss_17: 2.8584 - dense_1_loss_18: 2.9116 - dense_1_loss_19: 2.8234 - dense_1_loss_20: 2.8452 - dense_1_loss_21: 2.8927 - dense_1_loss_22: 2.7147 - dense_1_loss_23: 2.9386 - dense_1_loss_24: 2.9609 - dense_1_loss_25: 3.0370 - dense_1_loss_26: 2.6348 - dense_1_loss_27: 2.7733 - dense_1_loss_28: 2.7155 - dense_1_loss_29: 2.8941 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1167 - dense_1_acc_3: 0.1833 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2000 - dense_1_acc_6: 0.1833 - dense_1_acc_7: 0.1667 - dense_1_acc_8: 0.2667 - dense_1_acc_9: 0.2500 - dense_1_acc_10: 0.2000 - dense_1_acc_11: 0.2833 - dense_1_acc_12: 0.1667 - dense_1_acc_13: 0.2667 - dense_1_acc_14: 0.3000 - dense_1_acc_15: 0.2500 - dense_1_acc_16: 0.2000 - dense_1_acc_17: 0.2167 - dense_1_acc_18: 0.1667 - dense_1_acc_19: 0.2833 - dense_1_acc_20: 0.2167 - dense_1_acc_21: 0.2000 - dense_1_acc_22: 0.2500 - dense_1_acc_23: 0.1833 - dense_1_acc_24: 0.2000 - dense_1_acc_25: 0.1000 - dense_1_acc_26: 0.3167 - dense_1_acc_27: 0.2833 - dense_1_acc_28: 0.2833 - dense_1_acc_29: 0.2333 - dense_1_acc_30: 0.0333     
Epoch 13/100
60/60 [==============================] - 0s - loss: 83.6426 - dense_1_loss_1: 4.1859 - dense_1_loss_2: 3.9148 - dense_1_loss_3: 3.5556 - dense_1_loss_4: 3.3819 - dense_1_loss_5: 3.1457 - dense_1_loss_6: 3.1177 - dense_1_loss_7: 2.9987 - dense_1_loss_8: 2.7234 - dense_1_loss_9: 2.7472 - dense_1_loss_10: 2.6264 - dense_1_loss_11: 2.8023 - dense_1_loss_12: 2.7891 - dense_1_loss_13: 2.5696 - dense_1_loss_14: 2.6197 - dense_1_loss_15: 2.6712 - dense_1_loss_16: 2.8722 - dense_1_loss_17: 2.6568 - dense_1_loss_18: 2.7318 - dense_1_loss_19: 2.6588 - dense_1_loss_20: 2.6979 - dense_1_loss_21: 2.7737 - dense_1_loss_22: 2.5405 - dense_1_loss_23: 2.7616 - dense_1_loss_24: 2.8207 - dense_1_loss_25: 2.8322 - dense_1_loss_26: 2.4501 - dense_1_loss_27: 2.6474 - dense_1_loss_28: 2.6072 - dense_1_loss_29: 2.7424 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1167 - dense_1_acc_3: 0.1833 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2167 - dense_1_acc_6: 0.1667 - dense_1_acc_7: 0.2000 - dense_1_acc_8: 0.3000 - dense_1_acc_9: 0.2500 - dense_1_acc_10: 0.2333 - dense_1_acc_11: 0.2333 - dense_1_acc_12: 0.1167 - dense_1_acc_13: 0.2833 - dense_1_acc_14: 0.3167 - dense_1_acc_15: 0.2833 - dense_1_acc_16: 0.2000 - dense_1_acc_17: 0.2667 - dense_1_acc_18: 0.1833 - dense_1_acc_19: 0.2500 - dense_1_acc_20: 0.2333 - dense_1_acc_21: 0.1833 - dense_1_acc_22: 0.2500 - dense_1_acc_23: 0.2333 - dense_1_acc_24: 0.1667 - dense_1_acc_25: 0.1667 - dense_1_acc_26: 0.3500 - dense_1_acc_27: 0.2500 - dense_1_acc_28: 0.3333 - dense_1_acc_29: 0.1833 - dense_1_acc_30: 0.0167         
Epoch 14/100
60/60 [==============================] - 0s - loss: 80.1599 - dense_1_loss_1: 4.1773 - dense_1_loss_2: 3.8806 - dense_1_loss_3: 3.4963 - dense_1_loss_4: 3.2888 - dense_1_loss_5: 3.0315 - dense_1_loss_6: 2.9792 - dense_1_loss_7: 2.8666 - dense_1_loss_8: 2.5873 - dense_1_loss_9: 2.6216 - dense_1_loss_10: 2.4739 - dense_1_loss_11: 2.6523 - dense_1_loss_12: 2.6139 - dense_1_loss_13: 2.4499 - dense_1_loss_14: 2.5233 - dense_1_loss_15: 2.5437 - dense_1_loss_16: 2.7212 - dense_1_loss_17: 2.4917 - dense_1_loss_18: 2.5324 - dense_1_loss_19: 2.4546 - dense_1_loss_20: 2.5393 - dense_1_loss_21: 2.6648 - dense_1_loss_22: 2.3958 - dense_1_loss_23: 2.5646 - dense_1_loss_24: 2.7045 - dense_1_loss_25: 2.7259 - dense_1_loss_26: 2.3847 - dense_1_loss_27: 2.6512 - dense_1_loss_28: 2.5114 - dense_1_loss_29: 2.6317 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1833 - dense_1_acc_3: 0.1833 - dense_1_acc_4: 0.2667 - dense_1_acc_5: 0.2500 - dense_1_acc_6: 0.2167 - dense_1_acc_7: 0.2833 - dense_1_acc_8: 0.4000 - dense_1_acc_9: 0.2667 - dense_1_acc_10: 0.3167 - dense_1_acc_11: 0.3167 - dense_1_acc_12: 0.2000 - dense_1_acc_13: 0.2833 - dense_1_acc_14: 0.3167 - dense_1_acc_15: 0.3333 - dense_1_acc_16: 0.2833 - dense_1_acc_17: 0.3167 - dense_1_acc_18: 0.2667 - dense_1_acc_19: 0.3667 - dense_1_acc_20: 0.2333 - dense_1_acc_21: 0.2000 - dense_1_acc_22: 0.3333 - dense_1_acc_23: 0.3000 - dense_1_acc_24: 0.2333 - dense_1_acc_25: 0.1833 - dense_1_acc_26: 0.3000 - dense_1_acc_27: 0.2833 - dense_1_acc_28: 0.2667 - dense_1_acc_29: 0.2167 - dense_1_acc_30: 0.0000e+00     
Epoch 15/100
60/60 [==============================] - 0s - loss: 76.8179 - dense_1_loss_1: 4.1679 - dense_1_loss_2: 3.8467 - dense_1_loss_3: 3.4274 - dense_1_loss_4: 3.1926 - dense_1_loss_5: 2.9172 - dense_1_loss_6: 2.8500 - dense_1_loss_7: 2.7261 - dense_1_loss_8: 2.4658 - dense_1_loss_9: 2.5258 - dense_1_loss_10: 2.3815 - dense_1_loss_11: 2.5691 - dense_1_loss_12: 2.4863 - dense_1_loss_13: 2.3194 - dense_1_loss_14: 2.3739 - dense_1_loss_15: 2.4236 - dense_1_loss_16: 2.6003 - dense_1_loss_17: 2.3956 - dense_1_loss_18: 2.4197 - dense_1_loss_19: 2.3196 - dense_1_loss_20: 2.4612 - dense_1_loss_21: 2.5188 - dense_1_loss_22: 2.2973 - dense_1_loss_23: 2.4194 - dense_1_loss_24: 2.5428 - dense_1_loss_25: 2.5542 - dense_1_loss_26: 2.2412 - dense_1_loss_27: 2.5223 - dense_1_loss_28: 2.3844 - dense_1_loss_29: 2.4678 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1833 - dense_1_acc_3: 0.2333 - dense_1_acc_4: 0.2667 - dense_1_acc_5: 0.2500 - dense_1_acc_6: 0.2333 - dense_1_acc_7: 0.3333 - dense_1_acc_8: 0.3833 - dense_1_acc_9: 0.3167 - dense_1_acc_10: 0.3667 - dense_1_acc_11: 0.3667 - dense_1_acc_12: 0.2167 - dense_1_acc_13: 0.3500 - dense_1_acc_14: 0.3333 - dense_1_acc_15: 0.3167 - dense_1_acc_16: 0.2833 - dense_1_acc_17: 0.2833 - dense_1_acc_18: 0.3000 - dense_1_acc_19: 0.4000 - dense_1_acc_20: 0.2500 - dense_1_acc_21: 0.2333 - dense_1_acc_22: 0.3000 - dense_1_acc_23: 0.3333 - dense_1_acc_24: 0.2333 - dense_1_acc_25: 0.2500 - dense_1_acc_26: 0.3333 - dense_1_acc_27: 0.2333 - dense_1_acc_28: 0.3000 - dense_1_acc_29: 0.3000 - dense_1_acc_30: 0.0000e+00     
Epoch 16/100
60/60 [==============================] - 0s - loss: 73.4008 - dense_1_loss_1: 4.1579 - dense_1_loss_2: 3.8116 - dense_1_loss_3: 3.3479 - dense_1_loss_4: 3.0919 - dense_1_loss_5: 2.8011 - dense_1_loss_6: 2.7284 - dense_1_loss_7: 2.5883 - dense_1_loss_8: 2.3443 - dense_1_loss_9: 2.3937 - dense_1_loss_10: 2.2397 - dense_1_loss_11: 2.4660 - dense_1_loss_12: 2.3196 - dense_1_loss_13: 2.1630 - dense_1_loss_14: 2.2257 - dense_1_loss_15: 2.2710 - dense_1_loss_16: 2.4742 - dense_1_loss_17: 2.2683 - dense_1_loss_18: 2.3432 - dense_1_loss_19: 2.1594 - dense_1_loss_20: 2.3388 - dense_1_loss_21: 2.3345 - dense_1_loss_22: 2.2042 - dense_1_loss_23: 2.3488 - dense_1_loss_24: 2.4320 - dense_1_loss_25: 2.4266 - dense_1_loss_26: 2.1112 - dense_1_loss_27: 2.4265 - dense_1_loss_28: 2.2864 - dense_1_loss_29: 2.2966 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1833 - dense_1_acc_3: 0.2500 - dense_1_acc_4: 0.2333 - dense_1_acc_5: 0.2833 - dense_1_acc_6: 0.2667 - dense_1_acc_7: 0.3333 - dense_1_acc_8: 0.3833 - dense_1_acc_9: 0.3500 - dense_1_acc_10: 0.4167 - dense_1_acc_11: 0.3833 - dense_1_acc_12: 0.2667 - dense_1_acc_13: 0.3167 - dense_1_acc_14: 0.3833 - dense_1_acc_15: 0.3000 - dense_1_acc_16: 0.2500 - dense_1_acc_17: 0.3167 - dense_1_acc_18: 0.3333 - dense_1_acc_19: 0.4000 - dense_1_acc_20: 0.3167 - dense_1_acc_21: 0.2667 - dense_1_acc_22: 0.2333 - dense_1_acc_23: 0.2667 - dense_1_acc_24: 0.1667 - dense_1_acc_25: 0.2333 - dense_1_acc_26: 0.4000 - dense_1_acc_27: 0.2500 - dense_1_acc_28: 0.3167 - dense_1_acc_29: 0.3000 - dense_1_acc_30: 0.0000e+00     
Epoch 17/100
60/60 [==============================] - 0s - loss: 70.0872 - dense_1_loss_1: 4.1495 - dense_1_loss_2: 3.7729 - dense_1_loss_3: 3.2662 - dense_1_loss_4: 3.0011 - dense_1_loss_5: 2.6885 - dense_1_loss_6: 2.6056 - dense_1_loss_7: 2.4752 - dense_1_loss_8: 2.2551 - dense_1_loss_9: 2.3004 - dense_1_loss_10: 2.1027 - dense_1_loss_11: 2.3891 - dense_1_loss_12: 2.2100 - dense_1_loss_13: 2.0650 - dense_1_loss_14: 2.1590 - dense_1_loss_15: 2.1698 - dense_1_loss_16: 2.3357 - dense_1_loss_17: 2.1401 - dense_1_loss_18: 2.2150 - dense_1_loss_19: 2.0692 - dense_1_loss_20: 2.2291 - dense_1_loss_21: 2.1678 - dense_1_loss_22: 2.0886 - dense_1_loss_23: 2.2253 - dense_1_loss_24: 2.2170 - dense_1_loss_25: 2.2574 - dense_1_loss_26: 1.9940 - dense_1_loss_27: 2.2767 - dense_1_loss_28: 2.1200 - dense_1_loss_29: 2.1412 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1833 - dense_1_acc_3: 0.2167 - dense_1_acc_4: 0.2500 - dense_1_acc_5: 0.3000 - dense_1_acc_6: 0.3000 - dense_1_acc_7: 0.3500 - dense_1_acc_8: 0.4000 - dense_1_acc_9: 0.4000 - dense_1_acc_10: 0.5000 - dense_1_acc_11: 0.4000 - dense_1_acc_12: 0.3167 - dense_1_acc_13: 0.4167 - dense_1_acc_14: 0.4333 - dense_1_acc_15: 0.3667 - dense_1_acc_16: 0.2500 - dense_1_acc_17: 0.3833 - dense_1_acc_18: 0.3667 - dense_1_acc_19: 0.4000 - dense_1_acc_20: 0.3333 - dense_1_acc_21: 0.3333 - dense_1_acc_22: 0.3167 - dense_1_acc_23: 0.4000 - dense_1_acc_24: 0.2833 - dense_1_acc_25: 0.3167 - dense_1_acc_26: 0.5500 - dense_1_acc_27: 0.3167 - dense_1_acc_28: 0.3500 - dense_1_acc_29: 0.4000 - dense_1_acc_30: 0.0000e+00     
Epoch 18/100
60/60 [==============================] - 0s - loss: 67.0316 - dense_1_loss_1: 4.1408 - dense_1_loss_2: 3.7330 - dense_1_loss_3: 3.1909 - dense_1_loss_4: 2.9025 - dense_1_loss_5: 2.5840 - dense_1_loss_6: 2.4734 - dense_1_loss_7: 2.3792 - dense_1_loss_8: 2.1484 - dense_1_loss_9: 2.1922 - dense_1_loss_10: 1.9795 - dense_1_loss_11: 2.2536 - dense_1_loss_12: 2.0941 - dense_1_loss_13: 1.9490 - dense_1_loss_14: 2.1021 - dense_1_loss_15: 2.0741 - dense_1_loss_16: 2.2059 - dense_1_loss_17: 1.9888 - dense_1_loss_18: 2.0898 - dense_1_loss_19: 1.9388 - dense_1_loss_20: 2.1054 - dense_1_loss_21: 2.0783 - dense_1_loss_22: 1.9677 - dense_1_loss_23: 2.1150 - dense_1_loss_24: 2.1072 - dense_1_loss_25: 2.1418 - dense_1_loss_26: 1.8996 - dense_1_loss_27: 2.1575 - dense_1_loss_28: 2.0168 - dense_1_loss_29: 2.0224 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1667 - dense_1_acc_3: 0.2167 - dense_1_acc_4: 0.2500 - dense_1_acc_5: 0.3167 - dense_1_acc_6: 0.3333 - dense_1_acc_7: 0.3833 - dense_1_acc_8: 0.4667 - dense_1_acc_9: 0.4167 - dense_1_acc_10: 0.5333 - dense_1_acc_11: 0.4333 - dense_1_acc_12: 0.4000 - dense_1_acc_13: 0.5000 - dense_1_acc_14: 0.4500 - dense_1_acc_15: 0.3833 - dense_1_acc_16: 0.2833 - dense_1_acc_17: 0.4000 - dense_1_acc_18: 0.3333 - dense_1_acc_19: 0.4167 - dense_1_acc_20: 0.3833 - dense_1_acc_21: 0.3833 - dense_1_acc_22: 0.4833 - dense_1_acc_23: 0.3667 - dense_1_acc_24: 0.3833 - dense_1_acc_25: 0.3833 - dense_1_acc_26: 0.5500 - dense_1_acc_27: 0.3000 - dense_1_acc_28: 0.3500 - dense_1_acc_29: 0.4167 - dense_1_acc_30: 0.0000e+00     
Epoch 19/100
60/60 [==============================] - 0s - loss: 63.9432 - dense_1_loss_1: 4.1322 - dense_1_loss_2: 3.6946 - dense_1_loss_3: 3.1147 - dense_1_loss_4: 2.7986 - dense_1_loss_5: 2.4679 - dense_1_loss_6: 2.3453 - dense_1_loss_7: 2.2523 - dense_1_loss_8: 2.0245 - dense_1_loss_9: 2.0854 - dense_1_loss_10: 1.8802 - dense_1_loss_11: 2.1335 - dense_1_loss_12: 2.0015 - dense_1_loss_13: 1.8468 - dense_1_loss_14: 1.9451 - dense_1_loss_15: 1.9526 - dense_1_loss_16: 2.0801 - dense_1_loss_17: 1.8956 - dense_1_loss_18: 1.9663 - dense_1_loss_19: 1.8618 - dense_1_loss_20: 1.9999 - dense_1_loss_21: 1.9510 - dense_1_loss_22: 1.8284 - dense_1_loss_23: 2.0061 - dense_1_loss_24: 2.0085 - dense_1_loss_25: 2.0434 - dense_1_loss_26: 1.7892 - dense_1_loss_27: 2.0533 - dense_1_loss_28: 1.8866 - dense_1_loss_29: 1.8982 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1500 - dense_1_acc_3: 0.2333 - dense_1_acc_4: 0.2667 - dense_1_acc_5: 0.3500 - dense_1_acc_6: 0.3667 - dense_1_acc_7: 0.4000 - dense_1_acc_8: 0.5000 - dense_1_acc_9: 0.4500 - dense_1_acc_10: 0.5667 - dense_1_acc_11: 0.5000 - dense_1_acc_12: 0.3333 - dense_1_acc_13: 0.5500 - dense_1_acc_14: 0.4500 - dense_1_acc_15: 0.4833 - dense_1_acc_16: 0.3333 - dense_1_acc_17: 0.4167 - dense_1_acc_18: 0.4167 - dense_1_acc_19: 0.4500 - dense_1_acc_20: 0.4000 - dense_1_acc_21: 0.3667 - dense_1_acc_22: 0.4667 - dense_1_acc_23: 0.4000 - dense_1_acc_24: 0.3667 - dense_1_acc_25: 0.4000 - dense_1_acc_26: 0.5000 - dense_1_acc_27: 0.3000 - dense_1_acc_28: 0.4000 - dense_1_acc_29: 0.5500 - dense_1_acc_30: 0.0000e+00     
Epoch 20/100
60/60 [==============================] - 0s - loss: 60.9762 - dense_1_loss_1: 4.1233 - dense_1_loss_2: 3.6527 - dense_1_loss_3: 3.0345 - dense_1_loss_4: 2.7027 - dense_1_loss_5: 2.3684 - dense_1_loss_6: 2.2240 - dense_1_loss_7: 2.1266 - dense_1_loss_8: 1.9005 - dense_1_loss_9: 1.9860 - dense_1_loss_10: 1.7812 - dense_1_loss_11: 1.9898 - dense_1_loss_12: 1.8779 - dense_1_loss_13: 1.7453 - dense_1_loss_14: 1.8186 - dense_1_loss_15: 1.8542 - dense_1_loss_16: 1.9735 - dense_1_loss_17: 1.7790 - dense_1_loss_18: 1.8725 - dense_1_loss_19: 1.7151 - dense_1_loss_20: 1.8782 - dense_1_loss_21: 1.8475 - dense_1_loss_22: 1.6773 - dense_1_loss_23: 1.8620 - dense_1_loss_24: 1.9199 - dense_1_loss_25: 1.9638 - dense_1_loss_26: 1.7061 - dense_1_loss_27: 1.9535 - dense_1_loss_28: 1.7969 - dense_1_loss_29: 1.8452 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1500 - dense_1_acc_3: 0.2667 - dense_1_acc_4: 0.2833 - dense_1_acc_5: 0.3667 - dense_1_acc_6: 0.3833 - dense_1_acc_7: 0.4167 - dense_1_acc_8: 0.5167 - dense_1_acc_9: 0.5000 - dense_1_acc_10: 0.5667 - dense_1_acc_11: 0.5333 - dense_1_acc_12: 0.4667 - dense_1_acc_13: 0.5333 - dense_1_acc_14: 0.5000 - dense_1_acc_15: 0.4667 - dense_1_acc_16: 0.3667 - dense_1_acc_17: 0.4500 - dense_1_acc_18: 0.4167 - dense_1_acc_19: 0.4500 - dense_1_acc_20: 0.4500 - dense_1_acc_21: 0.4167 - dense_1_acc_22: 0.5167 - dense_1_acc_23: 0.4833 - dense_1_acc_24: 0.3667 - dense_1_acc_25: 0.3833 - dense_1_acc_26: 0.5167 - dense_1_acc_27: 0.4000 - dense_1_acc_28: 0.4000 - dense_1_acc_29: 0.4500 - dense_1_acc_30: 0.0000e+00     
Epoch 21/100
60/60 [==============================] - 0s - loss: 57.9695 - dense_1_loss_1: 4.1143 - dense_1_loss_2: 3.6085 - dense_1_loss_3: 2.9521 - dense_1_loss_4: 2.6046 - dense_1_loss_5: 2.2733 - dense_1_loss_6: 2.1071 - dense_1_loss_7: 2.0152 - dense_1_loss_8: 1.8106 - dense_1_loss_9: 1.8905 - dense_1_loss_10: 1.7123 - dense_1_loss_11: 1.8640 - dense_1_loss_12: 1.7759 - dense_1_loss_13: 1.6493 - dense_1_loss_14: 1.7390 - dense_1_loss_15: 1.7458 - dense_1_loss_16: 1.8555 - dense_1_loss_17: 1.6838 - dense_1_loss_18: 1.7210 - dense_1_loss_19: 1.5949 - dense_1_loss_20: 1.7405 - dense_1_loss_21: 1.7026 - dense_1_loss_22: 1.5848 - dense_1_loss_23: 1.6949 - dense_1_loss_24: 1.8004 - dense_1_loss_25: 1.8430 - dense_1_loss_26: 1.6585 - dense_1_loss_27: 1.8554 - dense_1_loss_28: 1.6628 - dense_1_loss_29: 1.7089 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.1667 - dense_1_acc_3: 0.3000 - dense_1_acc_4: 0.2833 - dense_1_acc_5: 0.3667 - dense_1_acc_6: 0.4333 - dense_1_acc_7: 0.4667 - dense_1_acc_8: 0.5000 - dense_1_acc_9: 0.4667 - dense_1_acc_10: 0.6167 - dense_1_acc_11: 0.5167 - dense_1_acc_12: 0.4333 - dense_1_acc_13: 0.5500 - dense_1_acc_14: 0.5667 - dense_1_acc_15: 0.4833 - dense_1_acc_16: 0.4000 - dense_1_acc_17: 0.4833 - dense_1_acc_18: 0.5000 - dense_1_acc_19: 0.7000 - dense_1_acc_20: 0.4667 - dense_1_acc_21: 0.5333 - dense_1_acc_22: 0.6333 - dense_1_acc_23: 0.5833 - dense_1_acc_24: 0.4667 - dense_1_acc_25: 0.4500 - dense_1_acc_26: 0.5667 - dense_1_acc_27: 0.4333 - dense_1_acc_28: 0.5833 - dense_1_acc_29: 0.5000 - dense_1_acc_30: 0.0000e+00     
Epoch 22/100
60/60 [==============================] - 0s - loss: 55.1693 - dense_1_loss_1: 4.1046 - dense_1_loss_2: 3.5621 - dense_1_loss_3: 2.8705 - dense_1_loss_4: 2.5036 - dense_1_loss_5: 2.1810 - dense_1_loss_6: 1.9914 - dense_1_loss_7: 1.9156 - dense_1_loss_8: 1.7098 - dense_1_loss_9: 1.7934 - dense_1_loss_10: 1.6279 - dense_1_loss_11: 1.7622 - dense_1_loss_12: 1.6565 - dense_1_loss_13: 1.5314 - dense_1_loss_14: 1.6551 - dense_1_loss_15: 1.6687 - dense_1_loss_16: 1.7482 - dense_1_loss_17: 1.6044 - dense_1_loss_18: 1.6243 - dense_1_loss_19: 1.4853 - dense_1_loss_20: 1.6108 - dense_1_loss_21: 1.5699 - dense_1_loss_22: 1.5424 - dense_1_loss_23: 1.6114 - dense_1_loss_24: 1.6697 - dense_1_loss_25: 1.7098 - dense_1_loss_26: 1.5661 - dense_1_loss_27: 1.7460 - dense_1_loss_28: 1.5501 - dense_1_loss_29: 1.5968 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2500 - dense_1_acc_3: 0.3167 - dense_1_acc_4: 0.3333 - dense_1_acc_5: 0.4333 - dense_1_acc_6: 0.5167 - dense_1_acc_7: 0.4667 - dense_1_acc_8: 0.5333 - dense_1_acc_9: 0.5333 - dense_1_acc_10: 0.6000 - dense_1_acc_11: 0.5833 - dense_1_acc_12: 0.5000 - dense_1_acc_13: 0.6500 - dense_1_acc_14: 0.5667 - dense_1_acc_15: 0.5167 - dense_1_acc_16: 0.4333 - dense_1_acc_17: 0.5500 - dense_1_acc_18: 0.5667 - dense_1_acc_19: 0.7167 - dense_1_acc_20: 0.6000 - dense_1_acc_21: 0.6667 - dense_1_acc_22: 0.6833 - dense_1_acc_23: 0.6833 - dense_1_acc_24: 0.5333 - dense_1_acc_25: 0.5333 - dense_1_acc_26: 0.6667 - dense_1_acc_27: 0.5167 - dense_1_acc_28: 0.6333 - dense_1_acc_29: 0.6333 - dense_1_acc_30: 0.0000e+00     
Epoch 23/100
60/60 [==============================] - 0s - loss: 52.3975 - dense_1_loss_1: 4.0942 - dense_1_loss_2: 3.5141 - dense_1_loss_3: 2.7861 - dense_1_loss_4: 2.3999 - dense_1_loss_5: 2.0870 - dense_1_loss_6: 1.8699 - dense_1_loss_7: 1.7951 - dense_1_loss_8: 1.6284 - dense_1_loss_9: 1.6844 - dense_1_loss_10: 1.5355 - dense_1_loss_11: 1.6405 - dense_1_loss_12: 1.5733 - dense_1_loss_13: 1.4455 - dense_1_loss_14: 1.5430 - dense_1_loss_15: 1.5585 - dense_1_loss_16: 1.6140 - dense_1_loss_17: 1.5253 - dense_1_loss_18: 1.4826 - dense_1_loss_19: 1.4451 - dense_1_loss_20: 1.4971 - dense_1_loss_21: 1.4700 - dense_1_loss_22: 1.4647 - dense_1_loss_23: 1.4979 - dense_1_loss_24: 1.5616 - dense_1_loss_25: 1.6112 - dense_1_loss_26: 1.4214 - dense_1_loss_27: 1.6411 - dense_1_loss_28: 1.4939 - dense_1_loss_29: 1.5165 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2500 - dense_1_acc_3: 0.3333 - dense_1_acc_4: 0.3333 - dense_1_acc_5: 0.4500 - dense_1_acc_6: 0.5333 - dense_1_acc_7: 0.5500 - dense_1_acc_8: 0.6000 - dense_1_acc_9: 0.6167 - dense_1_acc_10: 0.6333 - dense_1_acc_11: 0.5667 - dense_1_acc_12: 0.5667 - dense_1_acc_13: 0.6833 - dense_1_acc_14: 0.6000 - dense_1_acc_15: 0.5500 - dense_1_acc_16: 0.5000 - dense_1_acc_17: 0.6333 - dense_1_acc_18: 0.6500 - dense_1_acc_19: 0.7000 - dense_1_acc_20: 0.6333 - dense_1_acc_21: 0.6833 - dense_1_acc_22: 0.7000 - dense_1_acc_23: 0.6833 - dense_1_acc_24: 0.5167 - dense_1_acc_25: 0.5667 - dense_1_acc_26: 0.7000 - dense_1_acc_27: 0.5333 - dense_1_acc_28: 0.6167 - dense_1_acc_29: 0.6833 - dense_1_acc_30: 0.0000e+00     
Epoch 24/100
60/60 [==============================] - 0s - loss: 49.8612 - dense_1_loss_1: 4.0845 - dense_1_loss_2: 3.4662 - dense_1_loss_3: 2.7009 - dense_1_loss_4: 2.3050 - dense_1_loss_5: 2.0045 - dense_1_loss_6: 1.7770 - dense_1_loss_7: 1.6923 - dense_1_loss_8: 1.5566 - dense_1_loss_9: 1.5966 - dense_1_loss_10: 1.4576 - dense_1_loss_11: 1.5482 - dense_1_loss_12: 1.4850 - dense_1_loss_13: 1.3349 - dense_1_loss_14: 1.4190 - dense_1_loss_15: 1.4785 - dense_1_loss_16: 1.5273 - dense_1_loss_17: 1.4399 - dense_1_loss_18: 1.4006 - dense_1_loss_19: 1.3188 - dense_1_loss_20: 1.4236 - dense_1_loss_21: 1.3695 - dense_1_loss_22: 1.4125 - dense_1_loss_23: 1.3775 - dense_1_loss_24: 1.4485 - dense_1_loss_25: 1.5271 - dense_1_loss_26: 1.3703 - dense_1_loss_27: 1.5243 - dense_1_loss_28: 1.3830 - dense_1_loss_29: 1.4314 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2500 - dense_1_acc_3: 0.3667 - dense_1_acc_4: 0.3500 - dense_1_acc_5: 0.4833 - dense_1_acc_6: 0.5333 - dense_1_acc_7: 0.5667 - dense_1_acc_8: 0.6333 - dense_1_acc_9: 0.6000 - dense_1_acc_10: 0.6667 - dense_1_acc_11: 0.6667 - dense_1_acc_12: 0.6333 - dense_1_acc_13: 0.8167 - dense_1_acc_14: 0.6000 - dense_1_acc_15: 0.5500 - dense_1_acc_16: 0.5000 - dense_1_acc_17: 0.6500 - dense_1_acc_18: 0.5500 - dense_1_acc_19: 0.7333 - dense_1_acc_20: 0.6333 - dense_1_acc_21: 0.7167 - dense_1_acc_22: 0.5667 - dense_1_acc_23: 0.6333 - dense_1_acc_24: 0.5833 - dense_1_acc_25: 0.5333 - dense_1_acc_26: 0.6167 - dense_1_acc_27: 0.5333 - dense_1_acc_28: 0.6500 - dense_1_acc_29: 0.6167 - dense_1_acc_30: 0.0000e+00     
Epoch 25/100
60/60 [==============================] - 0s - loss: 47.3095 - dense_1_loss_1: 4.0752 - dense_1_loss_2: 3.4166 - dense_1_loss_3: 2.6164 - dense_1_loss_4: 2.2174 - dense_1_loss_5: 1.9134 - dense_1_loss_6: 1.6504 - dense_1_loss_7: 1.5878 - dense_1_loss_8: 1.4708 - dense_1_loss_9: 1.4866 - dense_1_loss_10: 1.3534 - dense_1_loss_11: 1.4858 - dense_1_loss_12: 1.3953 - dense_1_loss_13: 1.2642 - dense_1_loss_14: 1.3244 - dense_1_loss_15: 1.3672 - dense_1_loss_16: 1.4254 - dense_1_loss_17: 1.3420 - dense_1_loss_18: 1.3021 - dense_1_loss_19: 1.2639 - dense_1_loss_20: 1.3439 - dense_1_loss_21: 1.2832 - dense_1_loss_22: 1.3091 - dense_1_loss_23: 1.3155 - dense_1_loss_24: 1.3533 - dense_1_loss_25: 1.4162 - dense_1_loss_26: 1.2628 - dense_1_loss_27: 1.4020 - dense_1_loss_28: 1.3283 - dense_1_loss_29: 1.3366 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2500 - dense_1_acc_3: 0.4167 - dense_1_acc_4: 0.3500 - dense_1_acc_5: 0.5000 - dense_1_acc_6: 0.6000 - dense_1_acc_7: 0.6167 - dense_1_acc_8: 0.6333 - dense_1_acc_9: 0.7333 - dense_1_acc_10: 0.7500 - dense_1_acc_11: 0.6667 - dense_1_acc_12: 0.7000 - dense_1_acc_13: 0.8500 - dense_1_acc_14: 0.7000 - dense_1_acc_15: 0.6500 - dense_1_acc_16: 0.6333 - dense_1_acc_17: 0.7167 - dense_1_acc_18: 0.7167 - dense_1_acc_19: 0.7333 - dense_1_acc_20: 0.7333 - dense_1_acc_21: 0.7500 - dense_1_acc_22: 0.7000 - dense_1_acc_23: 0.7833 - dense_1_acc_24: 0.6667 - dense_1_acc_25: 0.6167 - dense_1_acc_26: 0.7000 - dense_1_acc_27: 0.6500 - dense_1_acc_28: 0.7833 - dense_1_acc_29: 0.8167 - dense_1_acc_30: 0.0000e+00         
Epoch 26/100
60/60 [==============================] - 0s - loss: 44.7418 - dense_1_loss_1: 4.0669 - dense_1_loss_2: 3.3653 - dense_1_loss_3: 2.5262 - dense_1_loss_4: 2.1127 - dense_1_loss_5: 1.8242 - dense_1_loss_6: 1.5331 - dense_1_loss_7: 1.4904 - dense_1_loss_8: 1.3923 - dense_1_loss_9: 1.3871 - dense_1_loss_10: 1.2844 - dense_1_loss_11: 1.3591 - dense_1_loss_12: 1.3019 - dense_1_loss_13: 1.1616 - dense_1_loss_14: 1.2026 - dense_1_loss_15: 1.2851 - dense_1_loss_16: 1.3355 - dense_1_loss_17: 1.2437 - dense_1_loss_18: 1.2225 - dense_1_loss_19: 1.1201 - dense_1_loss_20: 1.2829 - dense_1_loss_21: 1.1991 - dense_1_loss_22: 1.2353 - dense_1_loss_23: 1.2338 - dense_1_loss_24: 1.2478 - dense_1_loss_25: 1.3386 - dense_1_loss_26: 1.2025 - dense_1_loss_27: 1.3150 - dense_1_loss_28: 1.2356 - dense_1_loss_29: 1.2367 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2500 - dense_1_acc_3: 0.4500 - dense_1_acc_4: 0.3833 - dense_1_acc_5: 0.5333 - dense_1_acc_6: 0.6833 - dense_1_acc_7: 0.6667 - dense_1_acc_8: 0.6500 - dense_1_acc_9: 0.7333 - dense_1_acc_10: 0.7000 - dense_1_acc_11: 0.6667 - dense_1_acc_12: 0.7500 - dense_1_acc_13: 0.8500 - dense_1_acc_14: 0.7500 - dense_1_acc_15: 0.6667 - dense_1_acc_16: 0.6167 - dense_1_acc_17: 0.7167 - dense_1_acc_18: 0.6833 - dense_1_acc_19: 0.8333 - dense_1_acc_20: 0.7667 - dense_1_acc_21: 0.7500 - dense_1_acc_22: 0.7167 - dense_1_acc_23: 0.8167 - dense_1_acc_24: 0.7500 - dense_1_acc_25: 0.6500 - dense_1_acc_26: 0.7667 - dense_1_acc_27: 0.7000 - dense_1_acc_28: 0.8167 - dense_1_acc_29: 0.8333 - dense_1_acc_30: 0.0000e+00     
Epoch 27/100
60/60 [==============================] - 0s - loss: 42.3473 - dense_1_loss_1: 4.0590 - dense_1_loss_2: 3.3170 - dense_1_loss_3: 2.4496 - dense_1_loss_4: 2.0150 - dense_1_loss_5: 1.7344 - dense_1_loss_6: 1.4177 - dense_1_loss_7: 1.3943 - dense_1_loss_8: 1.3120 - dense_1_loss_9: 1.3041 - dense_1_loss_10: 1.2013 - dense_1_loss_11: 1.2862 - dense_1_loss_12: 1.2229 - dense_1_loss_13: 1.0812 - dense_1_loss_14: 1.1045 - dense_1_loss_15: 1.2135 - dense_1_loss_16: 1.2409 - dense_1_loss_17: 1.1661 - dense_1_loss_18: 1.1444 - dense_1_loss_19: 1.0816 - dense_1_loss_20: 1.1909 - dense_1_loss_21: 1.0955 - dense_1_loss_22: 1.1575 - dense_1_loss_23: 1.1553 - dense_1_loss_24: 1.1617 - dense_1_loss_25: 1.2230 - dense_1_loss_26: 1.1195 - dense_1_loss_27: 1.2440 - dense_1_loss_28: 1.1245 - dense_1_loss_29: 1.1298 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2667 - dense_1_acc_3: 0.5000 - dense_1_acc_4: 0.4833 - dense_1_acc_5: 0.5333 - dense_1_acc_6: 0.7333 - dense_1_acc_7: 0.7000 - dense_1_acc_8: 0.7167 - dense_1_acc_9: 0.7500 - dense_1_acc_10: 0.7833 - dense_1_acc_11: 0.7000 - dense_1_acc_12: 0.7833 - dense_1_acc_13: 0.8667 - dense_1_acc_14: 0.7500 - dense_1_acc_15: 0.7333 - dense_1_acc_16: 0.6667 - dense_1_acc_17: 0.7833 - dense_1_acc_18: 0.7500 - dense_1_acc_19: 0.9000 - dense_1_acc_20: 0.8000 - dense_1_acc_21: 0.8000 - dense_1_acc_22: 0.8167 - dense_1_acc_23: 0.8167 - dense_1_acc_24: 0.7500 - dense_1_acc_25: 0.7167 - dense_1_acc_26: 0.8167 - dense_1_acc_27: 0.7167 - dense_1_acc_28: 0.8333 - dense_1_acc_29: 0.8167 - dense_1_acc_30: 0.0000e+00     
Epoch 28/100
60/60 [==============================] - 0s - loss: 40.0189 - dense_1_loss_1: 4.0510 - dense_1_loss_2: 3.2670 - dense_1_loss_3: 2.3689 - dense_1_loss_4: 1.9204 - dense_1_loss_5: 1.6492 - dense_1_loss_6: 1.3242 - dense_1_loss_7: 1.2925 - dense_1_loss_8: 1.2187 - dense_1_loss_9: 1.2133 - dense_1_loss_10: 1.1198 - dense_1_loss_11: 1.2107 - dense_1_loss_12: 1.1277 - dense_1_loss_13: 1.0397 - dense_1_loss_14: 1.0482 - dense_1_loss_15: 1.1025 - dense_1_loss_16: 1.1389 - dense_1_loss_17: 1.0836 - dense_1_loss_18: 1.0320 - dense_1_loss_19: 1.0454 - dense_1_loss_20: 1.1080 - dense_1_loss_21: 1.0207 - dense_1_loss_22: 1.0523 - dense_1_loss_23: 1.0729 - dense_1_loss_24: 1.0764 - dense_1_loss_25: 1.1462 - dense_1_loss_26: 1.0269 - dense_1_loss_27: 1.1286 - dense_1_loss_28: 1.0683 - dense_1_loss_29: 1.0651 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2833 - dense_1_acc_3: 0.5000 - dense_1_acc_4: 0.5167 - dense_1_acc_5: 0.5333 - dense_1_acc_6: 0.7667 - dense_1_acc_7: 0.7167 - dense_1_acc_8: 0.7333 - dense_1_acc_9: 0.7667 - dense_1_acc_10: 0.8333 - dense_1_acc_11: 0.7333 - dense_1_acc_12: 0.8333 - dense_1_acc_13: 0.9000 - dense_1_acc_14: 0.7833 - dense_1_acc_15: 0.7667 - dense_1_acc_16: 0.7167 - dense_1_acc_17: 0.8333 - dense_1_acc_18: 0.8333 - dense_1_acc_19: 0.8833 - dense_1_acc_20: 0.8000 - dense_1_acc_21: 0.8667 - dense_1_acc_22: 0.8500 - dense_1_acc_23: 0.8167 - dense_1_acc_24: 0.8167 - dense_1_acc_25: 0.7500 - dense_1_acc_26: 0.8500 - dense_1_acc_27: 0.8000 - dense_1_acc_28: 0.8333 - dense_1_acc_29: 0.8333 - dense_1_acc_30: 0.0000e+00     
Epoch 29/100
60/60 [==============================] - 0s - loss: 37.8378 - dense_1_loss_1: 4.0432 - dense_1_loss_2: 3.2207 - dense_1_loss_3: 2.2905 - dense_1_loss_4: 1.8237 - dense_1_loss_5: 1.5633 - dense_1_loss_6: 1.2281 - dense_1_loss_7: 1.2080 - dense_1_loss_8: 1.1315 - dense_1_loss_9: 1.1119 - dense_1_loss_10: 1.0484 - dense_1_loss_11: 1.1197 - dense_1_loss_12: 1.0320 - dense_1_loss_13: 0.9443 - dense_1_loss_14: 0.9529 - dense_1_loss_15: 1.0497 - dense_1_loss_16: 1.0437 - dense_1_loss_17: 0.9947 - dense_1_loss_18: 0.9607 - dense_1_loss_19: 0.9454 - dense_1_loss_20: 1.0572 - dense_1_loss_21: 0.9677 - dense_1_loss_22: 1.0002 - dense_1_loss_23: 0.9986 - dense_1_loss_24: 0.9885 - dense_1_loss_25: 1.0736 - dense_1_loss_26: 0.9710 - dense_1_loss_27: 1.0585 - dense_1_loss_28: 0.9950 - dense_1_loss_29: 1.0150 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.2833 - dense_1_acc_3: 0.5167 - dense_1_acc_4: 0.5167 - dense_1_acc_5: 0.5667 - dense_1_acc_6: 0.7833 - dense_1_acc_7: 0.7833 - dense_1_acc_8: 0.8000 - dense_1_acc_9: 0.7833 - dense_1_acc_10: 0.8333 - dense_1_acc_11: 0.7667 - dense_1_acc_12: 0.8667 - dense_1_acc_13: 0.9167 - dense_1_acc_14: 0.8000 - dense_1_acc_15: 0.7333 - dense_1_acc_16: 0.8333 - dense_1_acc_17: 0.8833 - dense_1_acc_18: 0.9000 - dense_1_acc_19: 0.9333 - dense_1_acc_20: 0.8167 - dense_1_acc_21: 0.8833 - dense_1_acc_22: 0.8500 - dense_1_acc_23: 0.8833 - dense_1_acc_24: 0.8833 - dense_1_acc_25: 0.8167 - dense_1_acc_26: 0.8333 - dense_1_acc_27: 0.7667 - dense_1_acc_28: 0.8333 - dense_1_acc_29: 0.8667 - dense_1_acc_30: 0.0000e+00     
Epoch 30/100
60/60 [==============================] - 0s - loss: 35.7114 - dense_1_loss_1: 4.0357 - dense_1_loss_2: 3.1690 - dense_1_loss_3: 2.2164 - dense_1_loss_4: 1.7350 - dense_1_loss_5: 1.4730 - dense_1_loss_6: 1.1359 - dense_1_loss_7: 1.1130 - dense_1_loss_8: 1.0478 - dense_1_loss_9: 1.0402 - dense_1_loss_10: 0.9647 - dense_1_loss_11: 1.0418 - dense_1_loss_12: 0.9676 - dense_1_loss_13: 0.8939 - dense_1_loss_14: 0.9070 - dense_1_loss_15: 0.9718 - dense_1_loss_16: 0.9559 - dense_1_loss_17: 0.9306 - dense_1_loss_18: 0.8579 - dense_1_loss_19: 0.9251 - dense_1_loss_20: 0.9433 - dense_1_loss_21: 0.8857 - dense_1_loss_22: 0.9045 - dense_1_loss_23: 0.9313 - dense_1_loss_24: 0.9337 - dense_1_loss_25: 0.9969 - dense_1_loss_26: 0.9167 - dense_1_loss_27: 0.9693 - dense_1_loss_28: 0.9040 - dense_1_loss_29: 0.9436 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3000 - dense_1_acc_3: 0.5167 - dense_1_acc_4: 0.5167 - dense_1_acc_5: 0.6000 - dense_1_acc_6: 0.8667 - dense_1_acc_7: 0.8667 - dense_1_acc_8: 0.8000 - dense_1_acc_9: 0.8500 - dense_1_acc_10: 0.8667 - dense_1_acc_11: 0.8333 - dense_1_acc_12: 0.9000 - dense_1_acc_13: 0.9000 - dense_1_acc_14: 0.9167 - dense_1_acc_15: 0.8833 - dense_1_acc_16: 0.9000 - dense_1_acc_17: 0.9333 - dense_1_acc_18: 0.9500 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 0.9667 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 0.9667 - dense_1_acc_23: 0.9167 - dense_1_acc_24: 0.9333 - dense_1_acc_25: 0.9000 - dense_1_acc_26: 0.9333 - dense_1_acc_27: 0.8667 - dense_1_acc_28: 0.9500 - dense_1_acc_29: 0.9167 - dense_1_acc_30: 0.0000e+00     
Epoch 31/100
60/60 [==============================] - 0s - loss: 33.6327 - dense_1_loss_1: 4.0278 - dense_1_loss_2: 3.1247 - dense_1_loss_3: 2.1421 - dense_1_loss_4: 1.6395 - dense_1_loss_5: 1.3940 - dense_1_loss_6: 1.0398 - dense_1_loss_7: 1.0370 - dense_1_loss_8: 0.9715 - dense_1_loss_9: 0.9462 - dense_1_loss_10: 0.9004 - dense_1_loss_11: 0.9655 - dense_1_loss_12: 0.8800 - dense_1_loss_13: 0.8096 - dense_1_loss_14: 0.8173 - dense_1_loss_15: 0.9123 - dense_1_loss_16: 0.8922 - dense_1_loss_17: 0.8571 - dense_1_loss_18: 0.8004 - dense_1_loss_19: 0.8198 - dense_1_loss_20: 0.8860 - dense_1_loss_21: 0.8252 - dense_1_loss_22: 0.8438 - dense_1_loss_23: 0.8351 - dense_1_loss_24: 0.8626 - dense_1_loss_25: 0.9560 - dense_1_loss_26: 0.8363 - dense_1_loss_27: 0.8838 - dense_1_loss_28: 0.8535 - dense_1_loss_29: 0.8733 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3500 - dense_1_acc_3: 0.5167 - dense_1_acc_4: 0.6000 - dense_1_acc_5: 0.6667 - dense_1_acc_6: 0.8833 - dense_1_acc_7: 0.8833 - dense_1_acc_8: 0.8167 - dense_1_acc_9: 0.9167 - dense_1_acc_10: 0.8500 - dense_1_acc_11: 0.8500 - dense_1_acc_12: 0.9333 - dense_1_acc_13: 0.9333 - dense_1_acc_14: 0.9167 - dense_1_acc_15: 0.9167 - dense_1_acc_16: 0.9667 - dense_1_acc_17: 0.9333 - dense_1_acc_18: 0.9333 - dense_1_acc_19: 0.9667 - dense_1_acc_20: 0.9500 - dense_1_acc_21: 0.9500 - dense_1_acc_22: 0.9167 - dense_1_acc_23: 0.9333 - dense_1_acc_24: 0.9333 - dense_1_acc_25: 0.8833 - dense_1_acc_26: 0.9667 - dense_1_acc_27: 0.8667 - dense_1_acc_28: 0.9333 - dense_1_acc_29: 0.9167 - dense_1_acc_30: 0.0000e+00     
Epoch 32/100
60/60 [==============================] - 0s - loss: 31.7312 - dense_1_loss_1: 4.0205 - dense_1_loss_2: 3.0760 - dense_1_loss_3: 2.0688 - dense_1_loss_4: 1.5493 - dense_1_loss_5: 1.3121 - dense_1_loss_6: 0.9689 - dense_1_loss_7: 0.9446 - dense_1_loss_8: 0.9109 - dense_1_loss_9: 0.8673 - dense_1_loss_10: 0.8331 - dense_1_loss_11: 0.9033 - dense_1_loss_12: 0.8080 - dense_1_loss_13: 0.7393 - dense_1_loss_14: 0.7415 - dense_1_loss_15: 0.8443 - dense_1_loss_16: 0.8353 - dense_1_loss_17: 0.7862 - dense_1_loss_18: 0.7481 - dense_1_loss_19: 0.7705 - dense_1_loss_20: 0.8117 - dense_1_loss_21: 0.7597 - dense_1_loss_22: 0.7702 - dense_1_loss_23: 0.7924 - dense_1_loss_24: 0.7979 - dense_1_loss_25: 0.8652 - dense_1_loss_26: 0.7773 - dense_1_loss_27: 0.8238 - dense_1_loss_28: 0.7906 - dense_1_loss_29: 0.8143 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3500 - dense_1_acc_3: 0.5500 - dense_1_acc_4: 0.6167 - dense_1_acc_5: 0.6833 - dense_1_acc_6: 0.8833 - dense_1_acc_7: 0.9333 - dense_1_acc_8: 0.8500 - dense_1_acc_9: 0.9167 - dense_1_acc_10: 0.8833 - dense_1_acc_11: 0.8833 - dense_1_acc_12: 0.9500 - dense_1_acc_13: 0.9667 - dense_1_acc_14: 0.9833 - dense_1_acc_15: 0.9667 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 0.9667 - dense_1_acc_18: 0.9667 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 0.9667 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 0.9833 - dense_1_acc_23: 0.9667 - dense_1_acc_24: 0.9667 - dense_1_acc_25: 0.9333 - dense_1_acc_26: 0.9667 - dense_1_acc_27: 0.9167 - dense_1_acc_28: 0.9333 - dense_1_acc_29: 0.9333 - dense_1_acc_30: 0.0000e+00     
Epoch 33/100
60/60 [==============================] - 0s - loss: 29.9181 - dense_1_loss_1: 4.0138 - dense_1_loss_2: 3.0270 - dense_1_loss_3: 1.9968 - dense_1_loss_4: 1.4647 - dense_1_loss_5: 1.2359 - dense_1_loss_6: 0.9011 - dense_1_loss_7: 0.8651 - dense_1_loss_8: 0.8465 - dense_1_loss_9: 0.8044 - dense_1_loss_10: 0.7609 - dense_1_loss_11: 0.8563 - dense_1_loss_12: 0.7415 - dense_1_loss_13: 0.6783 - dense_1_loss_14: 0.7036 - dense_1_loss_15: 0.7781 - dense_1_loss_16: 0.7724 - dense_1_loss_17: 0.7189 - dense_1_loss_18: 0.6766 - dense_1_loss_19: 0.7246 - dense_1_loss_20: 0.7548 - dense_1_loss_21: 0.6779 - dense_1_loss_22: 0.7315 - dense_1_loss_23: 0.7184 - dense_1_loss_24: 0.7341 - dense_1_loss_25: 0.7936 - dense_1_loss_26: 0.7234 - dense_1_loss_27: 0.7645 - dense_1_loss_28: 0.7092 - dense_1_loss_29: 0.7443 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3667 - dense_1_acc_3: 0.5667 - dense_1_acc_4: 0.6333 - dense_1_acc_5: 0.6833 - dense_1_acc_6: 0.9167 - dense_1_acc_7: 0.9333 - dense_1_acc_8: 0.8833 - dense_1_acc_9: 0.9500 - dense_1_acc_10: 0.9333 - dense_1_acc_11: 0.8833 - dense_1_acc_12: 0.9500 - dense_1_acc_13: 0.9833 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 0.9333 - dense_1_acc_16: 0.9500 - dense_1_acc_17: 0.9667 - dense_1_acc_18: 0.9833 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 0.9833 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 0.9833 - dense_1_acc_23: 0.9667 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9167 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 0.9667 - dense_1_acc_28: 0.9500 - dense_1_acc_29: 0.9333 - dense_1_acc_30: 0.0000e+00     
Epoch 34/100
60/60 [==============================] - 0s - loss: 28.1843 - dense_1_loss_1: 4.0062 - dense_1_loss_2: 2.9812 - dense_1_loss_3: 1.9245 - dense_1_loss_4: 1.3828 - dense_1_loss_5: 1.1607 - dense_1_loss_6: 0.8414 - dense_1_loss_7: 0.7924 - dense_1_loss_8: 0.7707 - dense_1_loss_9: 0.7392 - dense_1_loss_10: 0.6991 - dense_1_loss_11: 0.7847 - dense_1_loss_12: 0.6773 - dense_1_loss_13: 0.6214 - dense_1_loss_14: 0.6399 - dense_1_loss_15: 0.7051 - dense_1_loss_16: 0.6978 - dense_1_loss_17: 0.6577 - dense_1_loss_18: 0.6188 - dense_1_loss_19: 0.6607 - dense_1_loss_20: 0.7072 - dense_1_loss_21: 0.6235 - dense_1_loss_22: 0.6757 - dense_1_loss_23: 0.6494 - dense_1_loss_24: 0.6878 - dense_1_loss_25: 0.7491 - dense_1_loss_26: 0.6797 - dense_1_loss_27: 0.6795 - dense_1_loss_28: 0.6712 - dense_1_loss_29: 0.6997 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4000 - dense_1_acc_3: 0.5833 - dense_1_acc_4: 0.6500 - dense_1_acc_5: 0.7333 - dense_1_acc_6: 0.9333 - dense_1_acc_7: 0.9333 - dense_1_acc_8: 0.9167 - dense_1_acc_9: 0.9500 - dense_1_acc_10: 0.9500 - dense_1_acc_11: 0.8833 - dense_1_acc_12: 0.9500 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 0.9833 - dense_1_acc_15: 0.9500 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9500 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 0.9833 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 35/100
60/60 [==============================] - 0s - loss: 26.6069 - dense_1_loss_1: 3.9991 - dense_1_loss_2: 2.9324 - dense_1_loss_3: 1.8514 - dense_1_loss_4: 1.3032 - dense_1_loss_5: 1.0932 - dense_1_loss_6: 0.7753 - dense_1_loss_7: 0.7331 - dense_1_loss_8: 0.7202 - dense_1_loss_9: 0.6753 - dense_1_loss_10: 0.6486 - dense_1_loss_11: 0.7218 - dense_1_loss_12: 0.6250 - dense_1_loss_13: 0.5704 - dense_1_loss_14: 0.5884 - dense_1_loss_15: 0.6421 - dense_1_loss_16: 0.6500 - dense_1_loss_17: 0.6026 - dense_1_loss_18: 0.5788 - dense_1_loss_19: 0.6175 - dense_1_loss_20: 0.6225 - dense_1_loss_21: 0.6041 - dense_1_loss_22: 0.6197 - dense_1_loss_23: 0.6220 - dense_1_loss_24: 0.6395 - dense_1_loss_25: 0.6802 - dense_1_loss_26: 0.6120 - dense_1_loss_27: 0.6324 - dense_1_loss_28: 0.6058 - dense_1_loss_29: 0.6402 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3833 - dense_1_acc_3: 0.5833 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.7667 - dense_1_acc_6: 0.9333 - dense_1_acc_7: 0.9500 - dense_1_acc_8: 0.9333 - dense_1_acc_9: 0.9500 - dense_1_acc_10: 0.9500 - dense_1_acc_11: 0.9000 - dense_1_acc_12: 0.9500 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 0.9833 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 0.9833 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9500 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 36/100
60/60 [==============================] - 0s - loss: 25.0740 - dense_1_loss_1: 3.9927 - dense_1_loss_2: 2.8843 - dense_1_loss_3: 1.7842 - dense_1_loss_4: 1.2211 - dense_1_loss_5: 1.0261 - dense_1_loss_6: 0.7134 - dense_1_loss_7: 0.6786 - dense_1_loss_8: 0.6676 - dense_1_loss_9: 0.6164 - dense_1_loss_10: 0.6071 - dense_1_loss_11: 0.6659 - dense_1_loss_12: 0.5657 - dense_1_loss_13: 0.5164 - dense_1_loss_14: 0.5467 - dense_1_loss_15: 0.6058 - dense_1_loss_16: 0.5934 - dense_1_loss_17: 0.5564 - dense_1_loss_18: 0.5251 - dense_1_loss_19: 0.5640 - dense_1_loss_20: 0.5797 - dense_1_loss_21: 0.5428 - dense_1_loss_22: 0.5694 - dense_1_loss_23: 0.5714 - dense_1_loss_24: 0.5786 - dense_1_loss_25: 0.6291 - dense_1_loss_26: 0.5552 - dense_1_loss_27: 0.5619 - dense_1_loss_28: 0.5623 - dense_1_loss_29: 0.5927 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.3833 - dense_1_acc_3: 0.5833 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.7667 - dense_1_acc_6: 0.9500 - dense_1_acc_7: 0.9333 - dense_1_acc_8: 0.9500 - dense_1_acc_9: 0.9500 - dense_1_acc_10: 0.9667 - dense_1_acc_11: 0.9333 - dense_1_acc_12: 0.9667 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 0.9833 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 0.9833 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9500 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 37/100
60/60 [==============================] - 0s - loss: 23.7223 - dense_1_loss_1: 3.9855 - dense_1_loss_2: 2.8369 - dense_1_loss_3: 1.7192 - dense_1_loss_4: 1.1475 - dense_1_loss_5: 0.9627 - dense_1_loss_6: 0.6601 - dense_1_loss_7: 0.6241 - dense_1_loss_8: 0.6056 - dense_1_loss_9: 0.5703 - dense_1_loss_10: 0.5528 - dense_1_loss_11: 0.6097 - dense_1_loss_12: 0.5221 - dense_1_loss_13: 0.4868 - dense_1_loss_14: 0.5048 - dense_1_loss_15: 0.5416 - dense_1_loss_16: 0.5317 - dense_1_loss_17: 0.5121 - dense_1_loss_18: 0.4678 - dense_1_loss_19: 0.5232 - dense_1_loss_20: 0.5394 - dense_1_loss_21: 0.4978 - dense_1_loss_22: 0.5246 - dense_1_loss_23: 0.5188 - dense_1_loss_24: 0.5400 - dense_1_loss_25: 0.6010 - dense_1_loss_26: 0.5200 - dense_1_loss_27: 0.5124 - dense_1_loss_28: 0.5371 - dense_1_loss_29: 0.5664 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4000 - dense_1_acc_3: 0.6167 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.8000 - dense_1_acc_6: 0.9333 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9667 - dense_1_acc_9: 0.9500 - dense_1_acc_10: 0.9667 - dense_1_acc_11: 0.9333 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9667 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 0.9833 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 38/100
60/60 [==============================] - 0s - loss: 22.3690 - dense_1_loss_1: 3.9788 - dense_1_loss_2: 2.7911 - dense_1_loss_3: 1.6587 - dense_1_loss_4: 1.0841 - dense_1_loss_5: 0.9021 - dense_1_loss_6: 0.6103 - dense_1_loss_7: 0.5715 - dense_1_loss_8: 0.5557 - dense_1_loss_9: 0.5230 - dense_1_loss_10: 0.4980 - dense_1_loss_11: 0.5581 - dense_1_loss_12: 0.4858 - dense_1_loss_13: 0.4419 - dense_1_loss_14: 0.4635 - dense_1_loss_15: 0.5008 - dense_1_loss_16: 0.4949 - dense_1_loss_17: 0.4657 - dense_1_loss_18: 0.4350 - dense_1_loss_19: 0.4623 - dense_1_loss_20: 0.4857 - dense_1_loss_21: 0.4766 - dense_1_loss_22: 0.4872 - dense_1_loss_23: 0.4822 - dense_1_loss_24: 0.4809 - dense_1_loss_25: 0.5382 - dense_1_loss_26: 0.4684 - dense_1_loss_27: 0.4809 - dense_1_loss_28: 0.4710 - dense_1_loss_29: 0.5165 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4000 - dense_1_acc_3: 0.6333 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.8167 - dense_1_acc_6: 0.9333 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 0.9667 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 0.9833 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9500 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 39/100
60/60 [==============================] - 0s - loss: 21.1719 - dense_1_loss_1: 3.9728 - dense_1_loss_2: 2.7437 - dense_1_loss_3: 1.6011 - dense_1_loss_4: 1.0229 - dense_1_loss_5: 0.8388 - dense_1_loss_6: 0.5639 - dense_1_loss_7: 0.5294 - dense_1_loss_8: 0.5076 - dense_1_loss_9: 0.4802 - dense_1_loss_10: 0.4507 - dense_1_loss_11: 0.5195 - dense_1_loss_12: 0.4461 - dense_1_loss_13: 0.4024 - dense_1_loss_14: 0.4270 - dense_1_loss_15: 0.4664 - dense_1_loss_16: 0.4571 - dense_1_loss_17: 0.4237 - dense_1_loss_18: 0.4000 - dense_1_loss_19: 0.4286 - dense_1_loss_20: 0.4509 - dense_1_loss_21: 0.4456 - dense_1_loss_22: 0.4418 - dense_1_loss_23: 0.4537 - dense_1_loss_24: 0.4345 - dense_1_loss_25: 0.4947 - dense_1_loss_26: 0.4336 - dense_1_loss_27: 0.4375 - dense_1_loss_28: 0.4344 - dense_1_loss_29: 0.4634 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4000 - dense_1_acc_3: 0.6333 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.8167 - dense_1_acc_6: 0.9500 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 0.9833 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 0.9833 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 40/100
60/60 [==============================] - 0s - loss: 20.0160 - dense_1_loss_1: 3.9667 - dense_1_loss_2: 2.6975 - dense_1_loss_3: 1.5447 - dense_1_loss_4: 0.9518 - dense_1_loss_5: 0.7832 - dense_1_loss_6: 0.5209 - dense_1_loss_7: 0.4853 - dense_1_loss_8: 0.4664 - dense_1_loss_9: 0.4378 - dense_1_loss_10: 0.4132 - dense_1_loss_11: 0.4690 - dense_1_loss_12: 0.4086 - dense_1_loss_13: 0.3720 - dense_1_loss_14: 0.3816 - dense_1_loss_15: 0.4299 - dense_1_loss_16: 0.4129 - dense_1_loss_17: 0.3967 - dense_1_loss_18: 0.3621 - dense_1_loss_19: 0.3926 - dense_1_loss_20: 0.4238 - dense_1_loss_21: 0.3987 - dense_1_loss_22: 0.4051 - dense_1_loss_23: 0.3990 - dense_1_loss_24: 0.4019 - dense_1_loss_25: 0.4626 - dense_1_loss_26: 0.4051 - dense_1_loss_27: 0.3911 - dense_1_loss_28: 0.4068 - dense_1_loss_29: 0.4291 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4167 - dense_1_acc_3: 0.6500 - dense_1_acc_4: 0.6667 - dense_1_acc_5: 0.8833 - dense_1_acc_6: 0.9500 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 0.9833 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 41/100
60/60 [==============================] - 0s - loss: 18.9549 - dense_1_loss_1: 3.9607 - dense_1_loss_2: 2.6507 - dense_1_loss_3: 1.4897 - dense_1_loss_4: 0.8904 - dense_1_loss_5: 0.7361 - dense_1_loss_6: 0.4851 - dense_1_loss_7: 0.4426 - dense_1_loss_8: 0.4276 - dense_1_loss_9: 0.4040 - dense_1_loss_10: 0.3747 - dense_1_loss_11: 0.4375 - dense_1_loss_12: 0.3714 - dense_1_loss_13: 0.3401 - dense_1_loss_14: 0.3593 - dense_1_loss_15: 0.3900 - dense_1_loss_16: 0.3793 - dense_1_loss_17: 0.3582 - dense_1_loss_18: 0.3307 - dense_1_loss_19: 0.3625 - dense_1_loss_20: 0.3837 - dense_1_loss_21: 0.3701 - dense_1_loss_22: 0.3769 - dense_1_loss_23: 0.3621 - dense_1_loss_24: 0.3642 - dense_1_loss_25: 0.4262 - dense_1_loss_26: 0.3615 - dense_1_loss_27: 0.3610 - dense_1_loss_28: 0.3649 - dense_1_loss_29: 0.3937 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4167 - dense_1_acc_3: 0.6500 - dense_1_acc_4: 0.6833 - dense_1_acc_5: 0.8667 - dense_1_acc_6: 0.9500 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 0.9833 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 0.9833 - dense_1_acc_25: 0.9833 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 42/100
60/60 [==============================] - 0s - loss: 17.9955 - dense_1_loss_1: 3.9545 - dense_1_loss_2: 2.6081 - dense_1_loss_3: 1.4368 - dense_1_loss_4: 0.8363 - dense_1_loss_5: 0.6876 - dense_1_loss_6: 0.4487 - dense_1_loss_7: 0.4118 - dense_1_loss_8: 0.3941 - dense_1_loss_9: 0.3777 - dense_1_loss_10: 0.3441 - dense_1_loss_11: 0.4058 - dense_1_loss_12: 0.3437 - dense_1_loss_13: 0.3078 - dense_1_loss_14: 0.3400 - dense_1_loss_15: 0.3551 - dense_1_loss_16: 0.3492 - dense_1_loss_17: 0.3272 - dense_1_loss_18: 0.3018 - dense_1_loss_19: 0.3322 - dense_1_loss_20: 0.3495 - dense_1_loss_21: 0.3438 - dense_1_loss_22: 0.3441 - dense_1_loss_23: 0.3318 - dense_1_loss_24: 0.3327 - dense_1_loss_25: 0.3832 - dense_1_loss_26: 0.3216 - dense_1_loss_27: 0.3299 - dense_1_loss_28: 0.3342 - dense_1_loss_29: 0.3623 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4167 - dense_1_acc_3: 0.6500 - dense_1_acc_4: 0.7000 - dense_1_acc_5: 0.9000 - dense_1_acc_6: 0.9500 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 0.9833 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9667 - dense_1_acc_30: 0.0000e+00     
Epoch 43/100
60/60 [==============================] - 0s - loss: 17.1029 - dense_1_loss_1: 3.9495 - dense_1_loss_2: 2.5627 - dense_1_loss_3: 1.3858 - dense_1_loss_4: 0.7848 - dense_1_loss_5: 0.6402 - dense_1_loss_6: 0.4154 - dense_1_loss_7: 0.3772 - dense_1_loss_8: 0.3615 - dense_1_loss_9: 0.3435 - dense_1_loss_10: 0.3181 - dense_1_loss_11: 0.3631 - dense_1_loss_12: 0.3151 - dense_1_loss_13: 0.2848 - dense_1_loss_14: 0.3048 - dense_1_loss_15: 0.3260 - dense_1_loss_16: 0.3193 - dense_1_loss_17: 0.3074 - dense_1_loss_18: 0.2777 - dense_1_loss_19: 0.3024 - dense_1_loss_20: 0.3285 - dense_1_loss_21: 0.3134 - dense_1_loss_22: 0.3127 - dense_1_loss_23: 0.3045 - dense_1_loss_24: 0.3058 - dense_1_loss_25: 0.3524 - dense_1_loss_26: 0.3026 - dense_1_loss_27: 0.2947 - dense_1_loss_28: 0.3158 - dense_1_loss_29: 0.3332 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.6667 - dense_1_acc_4: 0.7500 - dense_1_acc_5: 0.9000 - dense_1_acc_6: 0.9667 - dense_1_acc_7: 0.9667 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9667 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 44/100
60/60 [==============================] - 0s - loss: 16.2889 - dense_1_loss_1: 3.9439 - dense_1_loss_2: 2.5210 - dense_1_loss_3: 1.3375 - dense_1_loss_4: 0.7336 - dense_1_loss_5: 0.5985 - dense_1_loss_6: 0.3816 - dense_1_loss_7: 0.3453 - dense_1_loss_8: 0.3308 - dense_1_loss_9: 0.3129 - dense_1_loss_10: 0.2883 - dense_1_loss_11: 0.3258 - dense_1_loss_12: 0.2881 - dense_1_loss_13: 0.2613 - dense_1_loss_14: 0.2786 - dense_1_loss_15: 0.2970 - dense_1_loss_16: 0.2927 - dense_1_loss_17: 0.2837 - dense_1_loss_18: 0.2574 - dense_1_loss_19: 0.2748 - dense_1_loss_20: 0.3058 - dense_1_loss_21: 0.2895 - dense_1_loss_22: 0.2917 - dense_1_loss_23: 0.2790 - dense_1_loss_24: 0.2845 - dense_1_loss_25: 0.3304 - dense_1_loss_26: 0.2803 - dense_1_loss_27: 0.2717 - dense_1_loss_28: 0.2929 - dense_1_loss_29: 0.3102 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7000 - dense_1_acc_4: 0.8000 - dense_1_acc_5: 0.9167 - dense_1_acc_6: 0.9833 - dense_1_acc_7: 0.9833 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 0.9500 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 45/100
60/60 [==============================] - 0s - loss: 15.5217 - dense_1_loss_1: 3.9399 - dense_1_loss_2: 2.4787 - dense_1_loss_3: 1.2909 - dense_1_loss_4: 0.6906 - dense_1_loss_5: 0.5562 - dense_1_loss_6: 0.3540 - dense_1_loss_7: 0.3165 - dense_1_loss_8: 0.3055 - dense_1_loss_9: 0.2925 - dense_1_loss_10: 0.2635 - dense_1_loss_11: 0.2994 - dense_1_loss_12: 0.2681 - dense_1_loss_13: 0.2409 - dense_1_loss_14: 0.2615 - dense_1_loss_15: 0.2691 - dense_1_loss_16: 0.2713 - dense_1_loss_17: 0.2577 - dense_1_loss_18: 0.2360 - dense_1_loss_19: 0.2533 - dense_1_loss_20: 0.2738 - dense_1_loss_21: 0.2596 - dense_1_loss_22: 0.2761 - dense_1_loss_23: 0.2553 - dense_1_loss_24: 0.2557 - dense_1_loss_25: 0.3034 - dense_1_loss_26: 0.2544 - dense_1_loss_27: 0.2510 - dense_1_loss_28: 0.2548 - dense_1_loss_29: 0.2921 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7167 - dense_1_acc_4: 0.8333 - dense_1_acc_5: 0.9500 - dense_1_acc_6: 0.9833 - dense_1_acc_7: 0.9833 - dense_1_acc_8: 0.9833 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 46/100
60/60 [==============================] - 0s - loss: 14.8289 - dense_1_loss_1: 3.9344 - dense_1_loss_2: 2.4376 - dense_1_loss_3: 1.2483 - dense_1_loss_4: 0.6434 - dense_1_loss_5: 0.5192 - dense_1_loss_6: 0.3290 - dense_1_loss_7: 0.2938 - dense_1_loss_8: 0.2844 - dense_1_loss_9: 0.2705 - dense_1_loss_10: 0.2420 - dense_1_loss_11: 0.2738 - dense_1_loss_12: 0.2461 - dense_1_loss_13: 0.2214 - dense_1_loss_14: 0.2426 - dense_1_loss_15: 0.2458 - dense_1_loss_16: 0.2547 - dense_1_loss_17: 0.2324 - dense_1_loss_18: 0.2191 - dense_1_loss_19: 0.2370 - dense_1_loss_20: 0.2464 - dense_1_loss_21: 0.2495 - dense_1_loss_22: 0.2490 - dense_1_loss_23: 0.2336 - dense_1_loss_24: 0.2343 - dense_1_loss_25: 0.2795 - dense_1_loss_26: 0.2302 - dense_1_loss_27: 0.2320 - dense_1_loss_28: 0.2354 - dense_1_loss_29: 0.2632 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7333 - dense_1_acc_4: 0.8833 - dense_1_acc_5: 0.9500 - dense_1_acc_6: 0.9833 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 0.9833 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 47/100
60/60 [==============================] - 0s - loss: 14.1987 - dense_1_loss_1: 3.9300 - dense_1_loss_2: 2.3972 - dense_1_loss_3: 1.2059 - dense_1_loss_4: 0.6015 - dense_1_loss_5: 0.4850 - dense_1_loss_6: 0.3045 - dense_1_loss_7: 0.2734 - dense_1_loss_8: 0.2648 - dense_1_loss_9: 0.2446 - dense_1_loss_10: 0.2233 - dense_1_loss_11: 0.2517 - dense_1_loss_12: 0.2223 - dense_1_loss_13: 0.2037 - dense_1_loss_14: 0.2200 - dense_1_loss_15: 0.2305 - dense_1_loss_16: 0.2362 - dense_1_loss_17: 0.2207 - dense_1_loss_18: 0.2006 - dense_1_loss_19: 0.2116 - dense_1_loss_20: 0.2390 - dense_1_loss_21: 0.2264 - dense_1_loss_22: 0.2265 - dense_1_loss_23: 0.2126 - dense_1_loss_24: 0.2181 - dense_1_loss_25: 0.2626 - dense_1_loss_26: 0.2146 - dense_1_loss_27: 0.2110 - dense_1_loss_28: 0.2259 - dense_1_loss_29: 0.2344 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7500 - dense_1_acc_4: 0.8833 - dense_1_acc_5: 0.9500 - dense_1_acc_6: 0.9833 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 0.9833 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 48/100
60/60 [==============================] - 0s - loss: 13.5985 - dense_1_loss_1: 3.9258 - dense_1_loss_2: 2.3584 - dense_1_loss_3: 1.1657 - dense_1_loss_4: 0.5606 - dense_1_loss_5: 0.4527 - dense_1_loss_6: 0.2853 - dense_1_loss_7: 0.2516 - dense_1_loss_8: 0.2441 - dense_1_loss_9: 0.2283 - dense_1_loss_10: 0.2028 - dense_1_loss_11: 0.2304 - dense_1_loss_12: 0.2034 - dense_1_loss_13: 0.1905 - dense_1_loss_14: 0.2021 - dense_1_loss_15: 0.2116 - dense_1_loss_16: 0.2151 - dense_1_loss_17: 0.2061 - dense_1_loss_18: 0.1825 - dense_1_loss_19: 0.1946 - dense_1_loss_20: 0.2166 - dense_1_loss_21: 0.2091 - dense_1_loss_22: 0.2076 - dense_1_loss_23: 0.2014 - dense_1_loss_24: 0.1970 - dense_1_loss_25: 0.2408 - dense_1_loss_26: 0.1952 - dense_1_loss_27: 0.1929 - dense_1_loss_28: 0.2087 - dense_1_loss_29: 0.2177 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7500 - dense_1_acc_4: 0.9167 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 49/100
60/60 [==============================] - 0s - loss: 13.0738 - dense_1_loss_1: 3.9217 - dense_1_loss_2: 2.3209 - dense_1_loss_3: 1.1270 - dense_1_loss_4: 0.5304 - dense_1_loss_5: 0.4226 - dense_1_loss_6: 0.2644 - dense_1_loss_7: 0.2349 - dense_1_loss_8: 0.2249 - dense_1_loss_9: 0.2133 - dense_1_loss_10: 0.1857 - dense_1_loss_11: 0.2140 - dense_1_loss_12: 0.1889 - dense_1_loss_13: 0.1743 - dense_1_loss_14: 0.1923 - dense_1_loss_15: 0.1927 - dense_1_loss_16: 0.2030 - dense_1_loss_17: 0.1870 - dense_1_loss_18: 0.1700 - dense_1_loss_19: 0.1797 - dense_1_loss_20: 0.1988 - dense_1_loss_21: 0.1947 - dense_1_loss_22: 0.1940 - dense_1_loss_23: 0.1883 - dense_1_loss_24: 0.1795 - dense_1_loss_25: 0.2210 - dense_1_loss_26: 0.1801 - dense_1_loss_27: 0.1794 - dense_1_loss_28: 0.1885 - dense_1_loss_29: 0.2018 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7667 - dense_1_acc_4: 0.9333 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 0.9833 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 0.9833 - dense_1_acc_30: 0.0000e+00     
Epoch 50/100
60/60 [==============================] - 0s - loss: 12.5720 - dense_1_loss_1: 3.9175 - dense_1_loss_2: 2.2837 - dense_1_loss_3: 1.0895 - dense_1_loss_4: 0.4961 - dense_1_loss_5: 0.3949 - dense_1_loss_6: 0.2448 - dense_1_loss_7: 0.2170 - dense_1_loss_8: 0.2099 - dense_1_loss_9: 0.1954 - dense_1_loss_10: 0.1731 - dense_1_loss_11: 0.1919 - dense_1_loss_12: 0.1740 - dense_1_loss_13: 0.1612 - dense_1_loss_14: 0.1778 - dense_1_loss_15: 0.1770 - dense_1_loss_16: 0.1893 - dense_1_loss_17: 0.1733 - dense_1_loss_18: 0.1595 - dense_1_loss_19: 0.1643 - dense_1_loss_20: 0.1842 - dense_1_loss_21: 0.1777 - dense_1_loss_22: 0.1812 - dense_1_loss_23: 0.1700 - dense_1_loss_24: 0.1678 - dense_1_loss_25: 0.2018 - dense_1_loss_26: 0.1668 - dense_1_loss_27: 0.1648 - dense_1_loss_28: 0.1786 - dense_1_loss_29: 0.1889 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7667 - dense_1_acc_4: 0.9333 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 51/100
60/60 [==============================] - 0s - loss: 12.1297 - dense_1_loss_1: 3.9134 - dense_1_loss_2: 2.2470 - dense_1_loss_3: 1.0536 - dense_1_loss_4: 0.4658 - dense_1_loss_5: 0.3707 - dense_1_loss_6: 0.2284 - dense_1_loss_7: 0.2037 - dense_1_loss_8: 0.1979 - dense_1_loss_9: 0.1820 - dense_1_loss_10: 0.1633 - dense_1_loss_11: 0.1740 - dense_1_loss_12: 0.1602 - dense_1_loss_13: 0.1512 - dense_1_loss_14: 0.1618 - dense_1_loss_15: 0.1641 - dense_1_loss_16: 0.1765 - dense_1_loss_17: 0.1613 - dense_1_loss_18: 0.1476 - dense_1_loss_19: 0.1532 - dense_1_loss_20: 0.1698 - dense_1_loss_21: 0.1611 - dense_1_loss_22: 0.1702 - dense_1_loss_23: 0.1534 - dense_1_loss_24: 0.1578 - dense_1_loss_25: 0.1854 - dense_1_loss_26: 0.1566 - dense_1_loss_27: 0.1515 - dense_1_loss_28: 0.1711 - dense_1_loss_29: 0.1772 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7667 - dense_1_acc_4: 0.9500 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 52/100
60/60 [==============================] - 0s - loss: 11.7172 - dense_1_loss_1: 3.9096 - dense_1_loss_2: 2.2131 - dense_1_loss_3: 1.0204 - dense_1_loss_4: 0.4403 - dense_1_loss_5: 0.3487 - dense_1_loss_6: 0.2139 - dense_1_loss_7: 0.1899 - dense_1_loss_8: 0.1850 - dense_1_loss_9: 0.1707 - dense_1_loss_10: 0.1514 - dense_1_loss_11: 0.1624 - dense_1_loss_12: 0.1492 - dense_1_loss_13: 0.1386 - dense_1_loss_14: 0.1527 - dense_1_loss_15: 0.1525 - dense_1_loss_16: 0.1643 - dense_1_loss_17: 0.1508 - dense_1_loss_18: 0.1359 - dense_1_loss_19: 0.1422 - dense_1_loss_20: 0.1554 - dense_1_loss_21: 0.1545 - dense_1_loss_22: 0.1552 - dense_1_loss_23: 0.1433 - dense_1_loss_24: 0.1451 - dense_1_loss_25: 0.1747 - dense_1_loss_26: 0.1457 - dense_1_loss_27: 0.1390 - dense_1_loss_28: 0.1520 - dense_1_loss_29: 0.1609 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.7833 - dense_1_acc_4: 0.9500 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 53/100
60/60 [==============================] - 0s - loss: 11.3428 - dense_1_loss_1: 3.9054 - dense_1_loss_2: 2.1780 - dense_1_loss_3: 0.9901 - dense_1_loss_4: 0.4159 - dense_1_loss_5: 0.3268 - dense_1_loss_6: 0.2002 - dense_1_loss_7: 0.1777 - dense_1_loss_8: 0.1723 - dense_1_loss_9: 0.1593 - dense_1_loss_10: 0.1389 - dense_1_loss_11: 0.1526 - dense_1_loss_12: 0.1383 - dense_1_loss_13: 0.1278 - dense_1_loss_14: 0.1445 - dense_1_loss_15: 0.1422 - dense_1_loss_16: 0.1525 - dense_1_loss_17: 0.1401 - dense_1_loss_18: 0.1250 - dense_1_loss_19: 0.1316 - dense_1_loss_20: 0.1441 - dense_1_loss_21: 0.1442 - dense_1_loss_22: 0.1449 - dense_1_loss_23: 0.1342 - dense_1_loss_24: 0.1369 - dense_1_loss_25: 0.1601 - dense_1_loss_26: 0.1328 - dense_1_loss_27: 0.1294 - dense_1_loss_28: 0.1450 - dense_1_loss_29: 0.1521 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4333 - dense_1_acc_3: 0.8000 - dense_1_acc_4: 0.9500 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 54/100
60/60 [==============================] - 0s - loss: 10.9964 - dense_1_loss_1: 3.9014 - dense_1_loss_2: 2.1456 - dense_1_loss_3: 0.9598 - dense_1_loss_4: 0.3921 - dense_1_loss_5: 0.3058 - dense_1_loss_6: 0.1883 - dense_1_loss_7: 0.1654 - dense_1_loss_8: 0.1613 - dense_1_loss_9: 0.1486 - dense_1_loss_10: 0.1300 - dense_1_loss_11: 0.1416 - dense_1_loss_12: 0.1285 - dense_1_loss_13: 0.1204 - dense_1_loss_14: 0.1364 - dense_1_loss_15: 0.1310 - dense_1_loss_16: 0.1427 - dense_1_loss_17: 0.1304 - dense_1_loss_18: 0.1169 - dense_1_loss_19: 0.1244 - dense_1_loss_20: 0.1333 - dense_1_loss_21: 0.1319 - dense_1_loss_22: 0.1379 - dense_1_loss_23: 0.1233 - dense_1_loss_24: 0.1268 - dense_1_loss_25: 0.1489 - dense_1_loss_26: 0.1234 - dense_1_loss_27: 0.1219 - dense_1_loss_28: 0.1359 - dense_1_loss_29: 0.1425 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.4500 - dense_1_acc_3: 0.8000 - dense_1_acc_4: 0.9500 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 55/100
60/60 [==============================] - 0s - loss: 10.6827 - dense_1_loss_1: 3.8976 - dense_1_loss_2: 2.1121 - dense_1_loss_3: 0.9300 - dense_1_loss_4: 0.3725 - dense_1_loss_5: 0.2887 - dense_1_loss_6: 0.1784 - dense_1_loss_7: 0.1546 - dense_1_loss_8: 0.1540 - dense_1_loss_9: 0.1382 - dense_1_loss_10: 0.1223 - dense_1_loss_11: 0.1296 - dense_1_loss_12: 0.1204 - dense_1_loss_13: 0.1138 - dense_1_loss_14: 0.1240 - dense_1_loss_15: 0.1225 - dense_1_loss_16: 0.1353 - dense_1_loss_17: 0.1221 - dense_1_loss_18: 0.1107 - dense_1_loss_19: 0.1164 - dense_1_loss_20: 0.1257 - dense_1_loss_21: 0.1232 - dense_1_loss_22: 0.1280 - dense_1_loss_23: 0.1164 - dense_1_loss_24: 0.1187 - dense_1_loss_25: 0.1402 - dense_1_loss_26: 0.1165 - dense_1_loss_27: 0.1146 - dense_1_loss_28: 0.1245 - dense_1_loss_29: 0.1319 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5000 - dense_1_acc_3: 0.8167 - dense_1_acc_4: 0.9500 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 56/100
60/60 [==============================] - 0s - loss: 10.3850 - dense_1_loss_1: 3.8940 - dense_1_loss_2: 2.0815 - dense_1_loss_3: 0.9020 - dense_1_loss_4: 0.3528 - dense_1_loss_5: 0.2713 - dense_1_loss_6: 0.1672 - dense_1_loss_7: 0.1446 - dense_1_loss_8: 0.1439 - dense_1_loss_9: 0.1294 - dense_1_loss_10: 0.1139 - dense_1_loss_11: 0.1194 - dense_1_loss_12: 0.1126 - dense_1_loss_13: 0.1054 - dense_1_loss_14: 0.1148 - dense_1_loss_15: 0.1156 - dense_1_loss_16: 0.1274 - dense_1_loss_17: 0.1145 - dense_1_loss_18: 0.1046 - dense_1_loss_19: 0.1066 - dense_1_loss_20: 0.1185 - dense_1_loss_21: 0.1162 - dense_1_loss_22: 0.1186 - dense_1_loss_23: 0.1112 - dense_1_loss_24: 0.1116 - dense_1_loss_25: 0.1315 - dense_1_loss_26: 0.1097 - dense_1_loss_27: 0.1069 - dense_1_loss_28: 0.1167 - dense_1_loss_29: 0.1226 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5000 - dense_1_acc_3: 0.8167 - dense_1_acc_4: 0.9667 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 57/100
60/60 [==============================] - 0s - loss: 10.1131 - dense_1_loss_1: 3.8903 - dense_1_loss_2: 2.0500 - dense_1_loss_3: 0.8772 - dense_1_loss_4: 0.3349 - dense_1_loss_5: 0.2557 - dense_1_loss_6: 0.1585 - dense_1_loss_7: 0.1366 - dense_1_loss_8: 0.1350 - dense_1_loss_9: 0.1223 - dense_1_loss_10: 0.1060 - dense_1_loss_11: 0.1135 - dense_1_loss_12: 0.1064 - dense_1_loss_13: 0.0986 - dense_1_loss_14: 0.1090 - dense_1_loss_15: 0.1090 - dense_1_loss_16: 0.1189 - dense_1_loss_17: 0.1067 - dense_1_loss_18: 0.0965 - dense_1_loss_19: 0.0998 - dense_1_loss_20: 0.1104 - dense_1_loss_21: 0.1083 - dense_1_loss_22: 0.1106 - dense_1_loss_23: 0.1039 - dense_1_loss_24: 0.1044 - dense_1_loss_25: 0.1223 - dense_1_loss_26: 0.1023 - dense_1_loss_27: 0.1000 - dense_1_loss_28: 0.1105 - dense_1_loss_29: 0.1154 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5167 - dense_1_acc_3: 0.8167 - dense_1_acc_4: 0.9667 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 58/100
60/60 [==============================] - 0s - loss: 9.8662 - dense_1_loss_1: 3.8863 - dense_1_loss_2: 2.0200 - dense_1_loss_3: 0.8538 - dense_1_loss_4: 0.3189 - dense_1_loss_5: 0.2417 - dense_1_loss_6: 0.1509 - dense_1_loss_7: 0.1291 - dense_1_loss_8: 0.1273 - dense_1_loss_9: 0.1154 - dense_1_loss_10: 0.0994 - dense_1_loss_11: 0.1079 - dense_1_loss_12: 0.1002 - dense_1_loss_13: 0.0938 - dense_1_loss_14: 0.1034 - dense_1_loss_15: 0.1028 - dense_1_loss_16: 0.1110 - dense_1_loss_17: 0.1010 - dense_1_loss_18: 0.0898 - dense_1_loss_19: 0.0946 - dense_1_loss_20: 0.1036 - dense_1_loss_21: 0.1014 - dense_1_loss_22: 0.1043 - dense_1_loss_23: 0.0971 - dense_1_loss_24: 0.0969 - dense_1_loss_25: 0.1151 - dense_1_loss_26: 0.0951 - dense_1_loss_27: 0.0937 - dense_1_loss_28: 0.1038 - dense_1_loss_29: 0.1078 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5167 - dense_1_acc_3: 0.8167 - dense_1_acc_4: 0.9833 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00      
Epoch 59/100
60/60 [==============================] - 0s - loss: 9.6325 - dense_1_loss_1: 3.8830 - dense_1_loss_2: 1.9919 - dense_1_loss_3: 0.8286 - dense_1_loss_4: 0.3037 - dense_1_loss_5: 0.2279 - dense_1_loss_6: 0.1434 - dense_1_loss_7: 0.1213 - dense_1_loss_8: 0.1206 - dense_1_loss_9: 0.1079 - dense_1_loss_10: 0.0939 - dense_1_loss_11: 0.1010 - dense_1_loss_12: 0.0942 - dense_1_loss_13: 0.0880 - dense_1_loss_14: 0.0973 - dense_1_loss_15: 0.0967 - dense_1_loss_16: 0.1045 - dense_1_loss_17: 0.0952 - dense_1_loss_18: 0.0851 - dense_1_loss_19: 0.0883 - dense_1_loss_20: 0.0973 - dense_1_loss_21: 0.0960 - dense_1_loss_22: 0.0980 - dense_1_loss_23: 0.0912 - dense_1_loss_24: 0.0913 - dense_1_loss_25: 0.1094 - dense_1_loss_26: 0.0888 - dense_1_loss_27: 0.0885 - dense_1_loss_28: 0.0978 - dense_1_loss_29: 0.1016 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8167 - dense_1_acc_4: 0.9833 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 60/100
60/60 [==============================] - 0s - loss: 9.4190 - dense_1_loss_1: 3.8793 - dense_1_loss_2: 1.9633 - dense_1_loss_3: 0.8060 - dense_1_loss_4: 0.2891 - dense_1_loss_5: 0.2158 - dense_1_loss_6: 0.1355 - dense_1_loss_7: 0.1139 - dense_1_loss_8: 0.1144 - dense_1_loss_9: 0.1013 - dense_1_loss_10: 0.0886 - dense_1_loss_11: 0.0946 - dense_1_loss_12: 0.0886 - dense_1_loss_13: 0.0824 - dense_1_loss_14: 0.0910 - dense_1_loss_15: 0.0909 - dense_1_loss_16: 0.0991 - dense_1_loss_17: 0.0908 - dense_1_loss_18: 0.0812 - dense_1_loss_19: 0.0828 - dense_1_loss_20: 0.0921 - dense_1_loss_21: 0.0912 - dense_1_loss_22: 0.0929 - dense_1_loss_23: 0.0854 - dense_1_loss_24: 0.0869 - dense_1_loss_25: 0.1033 - dense_1_loss_26: 0.0848 - dense_1_loss_27: 0.0840 - dense_1_loss_28: 0.0935 - dense_1_loss_29: 0.0964 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8333 - dense_1_acc_4: 0.9833 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 61/100
60/60 [==============================] - 0s - loss: 9.2234 - dense_1_loss_1: 3.8756 - dense_1_loss_2: 1.9365 - dense_1_loss_3: 0.7849 - dense_1_loss_4: 0.2754 - dense_1_loss_5: 0.2058 - dense_1_loss_6: 0.1293 - dense_1_loss_7: 0.1077 - dense_1_loss_8: 0.1085 - dense_1_loss_9: 0.0962 - dense_1_loss_10: 0.0837 - dense_1_loss_11: 0.0900 - dense_1_loss_12: 0.0836 - dense_1_loss_13: 0.0783 - dense_1_loss_14: 0.0865 - dense_1_loss_15: 0.0849 - dense_1_loss_16: 0.0942 - dense_1_loss_17: 0.0857 - dense_1_loss_18: 0.0765 - dense_1_loss_19: 0.0789 - dense_1_loss_20: 0.0866 - dense_1_loss_21: 0.0849 - dense_1_loss_22: 0.0886 - dense_1_loss_23: 0.0802 - dense_1_loss_24: 0.0819 - dense_1_loss_25: 0.0966 - dense_1_loss_26: 0.0803 - dense_1_loss_27: 0.0804 - dense_1_loss_28: 0.0889 - dense_1_loss_29: 0.0932 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8500 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 62/100
60/60 [==============================] - 0s - loss: 9.0415 - dense_1_loss_1: 3.8721 - dense_1_loss_2: 1.9096 - dense_1_loss_3: 0.7654 - dense_1_loss_4: 0.2643 - dense_1_loss_5: 0.1956 - dense_1_loss_6: 0.1232 - dense_1_loss_7: 0.1023 - dense_1_loss_8: 0.1028 - dense_1_loss_9: 0.0914 - dense_1_loss_10: 0.0791 - dense_1_loss_11: 0.0860 - dense_1_loss_12: 0.0799 - dense_1_loss_13: 0.0741 - dense_1_loss_14: 0.0826 - dense_1_loss_15: 0.0806 - dense_1_loss_16: 0.0907 - dense_1_loss_17: 0.0805 - dense_1_loss_18: 0.0726 - dense_1_loss_19: 0.0748 - dense_1_loss_20: 0.0820 - dense_1_loss_21: 0.0809 - dense_1_loss_22: 0.0840 - dense_1_loss_23: 0.0759 - dense_1_loss_24: 0.0774 - dense_1_loss_25: 0.0913 - dense_1_loss_26: 0.0756 - dense_1_loss_27: 0.0760 - dense_1_loss_28: 0.0834 - dense_1_loss_29: 0.0873 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8500 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 0.9833 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 63/100
60/60 [==============================] - 0s - loss: 8.8690 - dense_1_loss_1: 3.8688 - dense_1_loss_2: 1.8842 - dense_1_loss_3: 0.7450 - dense_1_loss_4: 0.2523 - dense_1_loss_5: 0.1858 - dense_1_loss_6: 0.1177 - dense_1_loss_7: 0.0970 - dense_1_loss_8: 0.0979 - dense_1_loss_9: 0.0869 - dense_1_loss_10: 0.0745 - dense_1_loss_11: 0.0814 - dense_1_loss_12: 0.0760 - dense_1_loss_13: 0.0704 - dense_1_loss_14: 0.0782 - dense_1_loss_15: 0.0768 - dense_1_loss_16: 0.0862 - dense_1_loss_17: 0.0766 - dense_1_loss_18: 0.0686 - dense_1_loss_19: 0.0704 - dense_1_loss_20: 0.0779 - dense_1_loss_21: 0.0773 - dense_1_loss_22: 0.0791 - dense_1_loss_23: 0.0736 - dense_1_loss_24: 0.0731 - dense_1_loss_25: 0.0880 - dense_1_loss_26: 0.0724 - dense_1_loss_27: 0.0716 - dense_1_loss_28: 0.0795 - dense_1_loss_29: 0.0816 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8667 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 64/100
60/60 [==============================] - 0s - loss: 8.7089 - dense_1_loss_1: 3.8654 - dense_1_loss_2: 1.8598 - dense_1_loss_3: 0.7259 - dense_1_loss_4: 0.2419 - dense_1_loss_5: 0.1766 - dense_1_loss_6: 0.1130 - dense_1_loss_7: 0.0926 - dense_1_loss_8: 0.0931 - dense_1_loss_9: 0.0824 - dense_1_loss_10: 0.0710 - dense_1_loss_11: 0.0767 - dense_1_loss_12: 0.0721 - dense_1_loss_13: 0.0675 - dense_1_loss_14: 0.0739 - dense_1_loss_15: 0.0735 - dense_1_loss_16: 0.0810 - dense_1_loss_17: 0.0739 - dense_1_loss_18: 0.0655 - dense_1_loss_19: 0.0666 - dense_1_loss_20: 0.0739 - dense_1_loss_21: 0.0729 - dense_1_loss_22: 0.0754 - dense_1_loss_23: 0.0710 - dense_1_loss_24: 0.0697 - dense_1_loss_25: 0.0828 - dense_1_loss_26: 0.0697 - dense_1_loss_27: 0.0676 - dense_1_loss_28: 0.0762 - dense_1_loss_29: 0.0775 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8667 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 65/100
60/60 [==============================] - 0s - loss: 8.5620 - dense_1_loss_1: 3.8623 - dense_1_loss_2: 1.8358 - dense_1_loss_3: 0.7087 - dense_1_loss_4: 0.2318 - dense_1_loss_5: 0.1688 - dense_1_loss_6: 0.1083 - dense_1_loss_7: 0.0884 - dense_1_loss_8: 0.0892 - dense_1_loss_9: 0.0784 - dense_1_loss_10: 0.0678 - dense_1_loss_11: 0.0733 - dense_1_loss_12: 0.0689 - dense_1_loss_13: 0.0641 - dense_1_loss_14: 0.0703 - dense_1_loss_15: 0.0705 - dense_1_loss_16: 0.0777 - dense_1_loss_17: 0.0703 - dense_1_loss_18: 0.0623 - dense_1_loss_19: 0.0632 - dense_1_loss_20: 0.0708 - dense_1_loss_21: 0.0690 - dense_1_loss_22: 0.0718 - dense_1_loss_23: 0.0670 - dense_1_loss_24: 0.0666 - dense_1_loss_25: 0.0783 - dense_1_loss_26: 0.0664 - dense_1_loss_27: 0.0646 - dense_1_loss_28: 0.0728 - dense_1_loss_29: 0.0747 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8667 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 66/100
60/60 [==============================] - 0s - loss: 8.4204 - dense_1_loss_1: 3.8589 - dense_1_loss_2: 1.8127 - dense_1_loss_3: 0.6911 - dense_1_loss_4: 0.2227 - dense_1_loss_5: 0.1610 - dense_1_loss_6: 0.1041 - dense_1_loss_7: 0.0841 - dense_1_loss_8: 0.0853 - dense_1_loss_9: 0.0746 - dense_1_loss_10: 0.0649 - dense_1_loss_11: 0.0701 - dense_1_loss_12: 0.0659 - dense_1_loss_13: 0.0609 - dense_1_loss_14: 0.0674 - dense_1_loss_15: 0.0671 - dense_1_loss_16: 0.0753 - dense_1_loss_17: 0.0667 - dense_1_loss_18: 0.0591 - dense_1_loss_19: 0.0604 - dense_1_loss_20: 0.0679 - dense_1_loss_21: 0.0661 - dense_1_loss_22: 0.0684 - dense_1_loss_23: 0.0637 - dense_1_loss_24: 0.0632 - dense_1_loss_25: 0.0756 - dense_1_loss_26: 0.0621 - dense_1_loss_27: 0.0617 - dense_1_loss_28: 0.0686 - dense_1_loss_29: 0.0708 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8667 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 67/100
60/60 [==============================] - 0s - loss: 8.2915 - dense_1_loss_1: 3.8555 - dense_1_loss_2: 1.7900 - dense_1_loss_3: 0.6762 - dense_1_loss_4: 0.2143 - dense_1_loss_5: 0.1547 - dense_1_loss_6: 0.0999 - dense_1_loss_7: 0.0806 - dense_1_loss_8: 0.0815 - dense_1_loss_9: 0.0717 - dense_1_loss_10: 0.0619 - dense_1_loss_11: 0.0673 - dense_1_loss_12: 0.0632 - dense_1_loss_13: 0.0584 - dense_1_loss_14: 0.0647 - dense_1_loss_15: 0.0638 - dense_1_loss_16: 0.0723 - dense_1_loss_17: 0.0635 - dense_1_loss_18: 0.0565 - dense_1_loss_19: 0.0577 - dense_1_loss_20: 0.0644 - dense_1_loss_21: 0.0634 - dense_1_loss_22: 0.0657 - dense_1_loss_23: 0.0605 - dense_1_loss_24: 0.0605 - dense_1_loss_25: 0.0719 - dense_1_loss_26: 0.0591 - dense_1_loss_27: 0.0590 - dense_1_loss_28: 0.0660 - dense_1_loss_29: 0.0674 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8667 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 68/100
60/60 [==============================] - 0s - loss: 8.1680 - dense_1_loss_1: 3.8522 - dense_1_loss_2: 1.7677 - dense_1_loss_3: 0.6602 - dense_1_loss_4: 0.2057 - dense_1_loss_5: 0.1478 - dense_1_loss_6: 0.0962 - dense_1_loss_7: 0.0773 - dense_1_loss_8: 0.0780 - dense_1_loss_9: 0.0687 - dense_1_loss_10: 0.0590 - dense_1_loss_11: 0.0645 - dense_1_loss_12: 0.0604 - dense_1_loss_13: 0.0560 - dense_1_loss_14: 0.0620 - dense_1_loss_15: 0.0608 - dense_1_loss_16: 0.0682 - dense_1_loss_17: 0.0615 - dense_1_loss_18: 0.0540 - dense_1_loss_19: 0.0554 - dense_1_loss_20: 0.0609 - dense_1_loss_21: 0.0605 - dense_1_loss_22: 0.0633 - dense_1_loss_23: 0.0580 - dense_1_loss_24: 0.0581 - dense_1_loss_25: 0.0683 - dense_1_loss_26: 0.0572 - dense_1_loss_27: 0.0568 - dense_1_loss_28: 0.0636 - dense_1_loss_29: 0.0651 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 69/100
60/60 [==============================] - 0s - loss: 8.0531 - dense_1_loss_1: 3.8491 - dense_1_loss_2: 1.7468 - dense_1_loss_3: 0.6458 - dense_1_loss_4: 0.1982 - dense_1_loss_5: 0.1417 - dense_1_loss_6: 0.0928 - dense_1_loss_7: 0.0742 - dense_1_loss_8: 0.0749 - dense_1_loss_9: 0.0658 - dense_1_loss_10: 0.0567 - dense_1_loss_11: 0.0613 - dense_1_loss_12: 0.0579 - dense_1_loss_13: 0.0540 - dense_1_loss_14: 0.0591 - dense_1_loss_15: 0.0587 - dense_1_loss_16: 0.0649 - dense_1_loss_17: 0.0590 - dense_1_loss_18: 0.0520 - dense_1_loss_19: 0.0527 - dense_1_loss_20: 0.0585 - dense_1_loss_21: 0.0582 - dense_1_loss_22: 0.0605 - dense_1_loss_23: 0.0561 - dense_1_loss_24: 0.0558 - dense_1_loss_25: 0.0659 - dense_1_loss_26: 0.0552 - dense_1_loss_27: 0.0544 - dense_1_loss_28: 0.0613 - dense_1_loss_29: 0.0617 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 70/100
60/60 [==============================] - 0s - loss: 7.9420 - dense_1_loss_1: 3.8459 - dense_1_loss_2: 1.7251 - dense_1_loss_3: 0.6308 - dense_1_loss_4: 0.1912 - dense_1_loss_5: 0.1360 - dense_1_loss_6: 0.0896 - dense_1_loss_7: 0.0711 - dense_1_loss_8: 0.0721 - dense_1_loss_9: 0.0630 - dense_1_loss_10: 0.0546 - dense_1_loss_11: 0.0589 - dense_1_loss_12: 0.0556 - dense_1_loss_13: 0.0517 - dense_1_loss_14: 0.0567 - dense_1_loss_15: 0.0566 - dense_1_loss_16: 0.0626 - dense_1_loss_17: 0.0564 - dense_1_loss_18: 0.0499 - dense_1_loss_19: 0.0505 - dense_1_loss_20: 0.0568 - dense_1_loss_21: 0.0555 - dense_1_loss_22: 0.0580 - dense_1_loss_23: 0.0539 - dense_1_loss_24: 0.0534 - dense_1_loss_25: 0.0636 - dense_1_loss_26: 0.0528 - dense_1_loss_27: 0.0521 - dense_1_loss_28: 0.0588 - dense_1_loss_29: 0.0587 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 71/100
60/60 [==============================] - 0s - loss: 7.8401 - dense_1_loss_1: 3.8428 - dense_1_loss_2: 1.7059 - dense_1_loss_3: 0.6173 - dense_1_loss_4: 0.1843 - dense_1_loss_5: 0.1309 - dense_1_loss_6: 0.0865 - dense_1_loss_7: 0.0683 - dense_1_loss_8: 0.0694 - dense_1_loss_9: 0.0605 - dense_1_loss_10: 0.0526 - dense_1_loss_11: 0.0566 - dense_1_loss_12: 0.0536 - dense_1_loss_13: 0.0496 - dense_1_loss_14: 0.0546 - dense_1_loss_15: 0.0545 - dense_1_loss_16: 0.0605 - dense_1_loss_17: 0.0541 - dense_1_loss_18: 0.0481 - dense_1_loss_19: 0.0486 - dense_1_loss_20: 0.0547 - dense_1_loss_21: 0.0531 - dense_1_loss_22: 0.0556 - dense_1_loss_23: 0.0520 - dense_1_loss_24: 0.0513 - dense_1_loss_25: 0.0615 - dense_1_loss_26: 0.0504 - dense_1_loss_27: 0.0500 - dense_1_loss_28: 0.0565 - dense_1_loss_29: 0.0562 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.5500 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 72/100
60/60 [==============================] - 0s - loss: 7.7417 - dense_1_loss_1: 3.8397 - dense_1_loss_2: 1.6856 - dense_1_loss_3: 0.6039 - dense_1_loss_4: 0.1783 - dense_1_loss_5: 0.1262 - dense_1_loss_6: 0.0834 - dense_1_loss_7: 0.0660 - dense_1_loss_8: 0.0668 - dense_1_loss_9: 0.0583 - dense_1_loss_10: 0.0506 - dense_1_loss_11: 0.0545 - dense_1_loss_12: 0.0515 - dense_1_loss_13: 0.0476 - dense_1_loss_14: 0.0526 - dense_1_loss_15: 0.0522 - dense_1_loss_16: 0.0586 - dense_1_loss_17: 0.0519 - dense_1_loss_18: 0.0462 - dense_1_loss_19: 0.0467 - dense_1_loss_20: 0.0525 - dense_1_loss_21: 0.0511 - dense_1_loss_22: 0.0536 - dense_1_loss_23: 0.0498 - dense_1_loss_24: 0.0494 - dense_1_loss_25: 0.0587 - dense_1_loss_26: 0.0483 - dense_1_loss_27: 0.0481 - dense_1_loss_28: 0.0547 - dense_1_loss_29: 0.0548 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 73/100
60/60 [==============================] - 0s - loss: 7.6506 - dense_1_loss_1: 3.8364 - dense_1_loss_2: 1.6670 - dense_1_loss_3: 0.5915 - dense_1_loss_4: 0.1727 - dense_1_loss_5: 0.1218 - dense_1_loss_6: 0.0806 - dense_1_loss_7: 0.0637 - dense_1_loss_8: 0.0643 - dense_1_loss_9: 0.0564 - dense_1_loss_10: 0.0487 - dense_1_loss_11: 0.0526 - dense_1_loss_12: 0.0498 - dense_1_loss_13: 0.0458 - dense_1_loss_14: 0.0507 - dense_1_loss_15: 0.0504 - dense_1_loss_16: 0.0566 - dense_1_loss_17: 0.0502 - dense_1_loss_18: 0.0445 - dense_1_loss_19: 0.0451 - dense_1_loss_20: 0.0501 - dense_1_loss_21: 0.0496 - dense_1_loss_22: 0.0516 - dense_1_loss_23: 0.0483 - dense_1_loss_24: 0.0477 - dense_1_loss_25: 0.0566 - dense_1_loss_26: 0.0466 - dense_1_loss_27: 0.0463 - dense_1_loss_28: 0.0526 - dense_1_loss_29: 0.0526 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 74/100
60/60 [==============================] - 0s - loss: 7.5613 - dense_1_loss_1: 3.8333 - dense_1_loss_2: 1.6487 - dense_1_loss_3: 0.5789 - dense_1_loss_4: 0.1670 - dense_1_loss_5: 0.1170 - dense_1_loss_6: 0.0780 - dense_1_loss_7: 0.0614 - dense_1_loss_8: 0.0620 - dense_1_loss_9: 0.0543 - dense_1_loss_10: 0.0469 - dense_1_loss_11: 0.0506 - dense_1_loss_12: 0.0480 - dense_1_loss_13: 0.0443 - dense_1_loss_14: 0.0487 - dense_1_loss_15: 0.0487 - dense_1_loss_16: 0.0546 - dense_1_loss_17: 0.0486 - dense_1_loss_18: 0.0428 - dense_1_loss_19: 0.0434 - dense_1_loss_20: 0.0481 - dense_1_loss_21: 0.0480 - dense_1_loss_22: 0.0499 - dense_1_loss_23: 0.0466 - dense_1_loss_24: 0.0460 - dense_1_loss_25: 0.0547 - dense_1_loss_26: 0.0451 - dense_1_loss_27: 0.0448 - dense_1_loss_28: 0.0506 - dense_1_loss_29: 0.0504 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 75/100
60/60 [==============================] - 0s - loss: 7.4787 - dense_1_loss_1: 3.8305 - dense_1_loss_2: 1.6306 - dense_1_loss_3: 0.5667 - dense_1_loss_4: 0.1621 - dense_1_loss_5: 0.1128 - dense_1_loss_6: 0.0756 - dense_1_loss_7: 0.0594 - dense_1_loss_8: 0.0600 - dense_1_loss_9: 0.0524 - dense_1_loss_10: 0.0453 - dense_1_loss_11: 0.0490 - dense_1_loss_12: 0.0464 - dense_1_loss_13: 0.0429 - dense_1_loss_14: 0.0469 - dense_1_loss_15: 0.0472 - dense_1_loss_16: 0.0525 - dense_1_loss_17: 0.0471 - dense_1_loss_18: 0.0413 - dense_1_loss_19: 0.0419 - dense_1_loss_20: 0.0466 - dense_1_loss_21: 0.0462 - dense_1_loss_22: 0.0483 - dense_1_loss_23: 0.0452 - dense_1_loss_24: 0.0444 - dense_1_loss_25: 0.0529 - dense_1_loss_26: 0.0435 - dense_1_loss_27: 0.0434 - dense_1_loss_28: 0.0491 - dense_1_loss_29: 0.0488 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 76/100
60/60 [==============================] - 0s - loss: 7.3988 - dense_1_loss_1: 3.8274 - dense_1_loss_2: 1.6132 - dense_1_loss_3: 0.5554 - dense_1_loss_4: 0.1570 - dense_1_loss_5: 0.1090 - dense_1_loss_6: 0.0732 - dense_1_loss_7: 0.0573 - dense_1_loss_8: 0.0581 - dense_1_loss_9: 0.0505 - dense_1_loss_10: 0.0438 - dense_1_loss_11: 0.0473 - dense_1_loss_12: 0.0448 - dense_1_loss_13: 0.0416 - dense_1_loss_14: 0.0453 - dense_1_loss_15: 0.0458 - dense_1_loss_16: 0.0506 - dense_1_loss_17: 0.0454 - dense_1_loss_18: 0.0399 - dense_1_loss_19: 0.0404 - dense_1_loss_20: 0.0453 - dense_1_loss_21: 0.0445 - dense_1_loss_22: 0.0465 - dense_1_loss_23: 0.0438 - dense_1_loss_24: 0.0429 - dense_1_loss_25: 0.0514 - dense_1_loss_26: 0.0417 - dense_1_loss_27: 0.0419 - dense_1_loss_28: 0.0474 - dense_1_loss_29: 0.0473 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 77/100
60/60 [==============================] - 0s - loss: 7.3247 - dense_1_loss_1: 3.8245 - dense_1_loss_2: 1.5963 - dense_1_loss_3: 0.5444 - dense_1_loss_4: 0.1525 - dense_1_loss_5: 0.1059 - dense_1_loss_6: 0.0710 - dense_1_loss_7: 0.0556 - dense_1_loss_8: 0.0564 - dense_1_loss_9: 0.0489 - dense_1_loss_10: 0.0424 - dense_1_loss_11: 0.0458 - dense_1_loss_12: 0.0432 - dense_1_loss_13: 0.0403 - dense_1_loss_14: 0.0439 - dense_1_loss_15: 0.0443 - dense_1_loss_16: 0.0488 - dense_1_loss_17: 0.0439 - dense_1_loss_18: 0.0387 - dense_1_loss_19: 0.0391 - dense_1_loss_20: 0.0440 - dense_1_loss_21: 0.0428 - dense_1_loss_22: 0.0451 - dense_1_loss_23: 0.0424 - dense_1_loss_24: 0.0416 - dense_1_loss_25: 0.0496 - dense_1_loss_26: 0.0405 - dense_1_loss_27: 0.0406 - dense_1_loss_28: 0.0460 - dense_1_loss_29: 0.0460 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6000 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 78/100
60/60 [==============================] - 0s - loss: 7.2522 - dense_1_loss_1: 3.8213 - dense_1_loss_2: 1.5798 - dense_1_loss_3: 0.5340 - dense_1_loss_4: 0.1481 - dense_1_loss_5: 0.1028 - dense_1_loss_6: 0.0688 - dense_1_loss_7: 0.0538 - dense_1_loss_8: 0.0546 - dense_1_loss_9: 0.0474 - dense_1_loss_10: 0.0411 - dense_1_loss_11: 0.0443 - dense_1_loss_12: 0.0418 - dense_1_loss_13: 0.0391 - dense_1_loss_14: 0.0427 - dense_1_loss_15: 0.0426 - dense_1_loss_16: 0.0474 - dense_1_loss_17: 0.0424 - dense_1_loss_18: 0.0375 - dense_1_loss_19: 0.0380 - dense_1_loss_20: 0.0424 - dense_1_loss_21: 0.0416 - dense_1_loss_22: 0.0438 - dense_1_loss_23: 0.0410 - dense_1_loss_24: 0.0403 - dense_1_loss_25: 0.0479 - dense_1_loss_26: 0.0393 - dense_1_loss_27: 0.0394 - dense_1_loss_28: 0.0446 - dense_1_loss_29: 0.0446 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6167 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 79/100
60/60 [==============================] - 0s - loss: 7.1811 - dense_1_loss_1: 3.8186 - dense_1_loss_2: 1.5638 - dense_1_loss_3: 0.5222 - dense_1_loss_4: 0.1437 - dense_1_loss_5: 0.0994 - dense_1_loss_6: 0.0669 - dense_1_loss_7: 0.0521 - dense_1_loss_8: 0.0529 - dense_1_loss_9: 0.0458 - dense_1_loss_10: 0.0399 - dense_1_loss_11: 0.0428 - dense_1_loss_12: 0.0406 - dense_1_loss_13: 0.0377 - dense_1_loss_14: 0.0413 - dense_1_loss_15: 0.0414 - dense_1_loss_16: 0.0462 - dense_1_loss_17: 0.0410 - dense_1_loss_18: 0.0364 - dense_1_loss_19: 0.0367 - dense_1_loss_20: 0.0410 - dense_1_loss_21: 0.0403 - dense_1_loss_22: 0.0424 - dense_1_loss_23: 0.0398 - dense_1_loss_24: 0.0390 - dense_1_loss_25: 0.0464 - dense_1_loss_26: 0.0382 - dense_1_loss_27: 0.0384 - dense_1_loss_28: 0.0431 - dense_1_loss_29: 0.0430 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 80/100
60/60 [==============================] - 0s - loss: 7.1152 - dense_1_loss_1: 3.8156 - dense_1_loss_2: 1.5478 - dense_1_loss_3: 0.5125 - dense_1_loss_4: 0.1404 - dense_1_loss_5: 0.0966 - dense_1_loss_6: 0.0650 - dense_1_loss_7: 0.0507 - dense_1_loss_8: 0.0512 - dense_1_loss_9: 0.0445 - dense_1_loss_10: 0.0387 - dense_1_loss_11: 0.0416 - dense_1_loss_12: 0.0394 - dense_1_loss_13: 0.0366 - dense_1_loss_14: 0.0399 - dense_1_loss_15: 0.0403 - dense_1_loss_16: 0.0449 - dense_1_loss_17: 0.0397 - dense_1_loss_18: 0.0353 - dense_1_loss_19: 0.0355 - dense_1_loss_20: 0.0396 - dense_1_loss_21: 0.0392 - dense_1_loss_22: 0.0413 - dense_1_loss_23: 0.0387 - dense_1_loss_24: 0.0378 - dense_1_loss_25: 0.0449 - dense_1_loss_26: 0.0369 - dense_1_loss_27: 0.0374 - dense_1_loss_28: 0.0416 - dense_1_loss_29: 0.0416 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 81/100
60/60 [==============================] - 0s - loss: 7.0509 - dense_1_loss_1: 3.8127 - dense_1_loss_2: 1.5323 - dense_1_loss_3: 0.5026 - dense_1_loss_4: 0.1366 - dense_1_loss_5: 0.0936 - dense_1_loss_6: 0.0634 - dense_1_loss_7: 0.0492 - dense_1_loss_8: 0.0497 - dense_1_loss_9: 0.0431 - dense_1_loss_10: 0.0376 - dense_1_loss_11: 0.0405 - dense_1_loss_12: 0.0383 - dense_1_loss_13: 0.0355 - dense_1_loss_14: 0.0386 - dense_1_loss_15: 0.0392 - dense_1_loss_16: 0.0434 - dense_1_loss_17: 0.0385 - dense_1_loss_18: 0.0342 - dense_1_loss_19: 0.0344 - dense_1_loss_20: 0.0385 - dense_1_loss_21: 0.0379 - dense_1_loss_22: 0.0401 - dense_1_loss_23: 0.0375 - dense_1_loss_24: 0.0367 - dense_1_loss_25: 0.0436 - dense_1_loss_26: 0.0358 - dense_1_loss_27: 0.0364 - dense_1_loss_28: 0.0405 - dense_1_loss_29: 0.0405 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 82/100
60/60 [==============================] - 0s - loss: 6.9908 - dense_1_loss_1: 3.8098 - dense_1_loss_2: 1.5177 - dense_1_loss_3: 0.4935 - dense_1_loss_4: 0.1331 - dense_1_loss_5: 0.0913 - dense_1_loss_6: 0.0617 - dense_1_loss_7: 0.0478 - dense_1_loss_8: 0.0483 - dense_1_loss_9: 0.0418 - dense_1_loss_10: 0.0365 - dense_1_loss_11: 0.0394 - dense_1_loss_12: 0.0372 - dense_1_loss_13: 0.0346 - dense_1_loss_14: 0.0377 - dense_1_loss_15: 0.0380 - dense_1_loss_16: 0.0421 - dense_1_loss_17: 0.0374 - dense_1_loss_18: 0.0333 - dense_1_loss_19: 0.0335 - dense_1_loss_20: 0.0375 - dense_1_loss_21: 0.0368 - dense_1_loss_22: 0.0389 - dense_1_loss_23: 0.0365 - dense_1_loss_24: 0.0357 - dense_1_loss_25: 0.0426 - dense_1_loss_26: 0.0347 - dense_1_loss_27: 0.0350 - dense_1_loss_28: 0.0394 - dense_1_loss_29: 0.0392 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.8833 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 83/100
60/60 [==============================] - 0s - loss: 6.9298 - dense_1_loss_1: 3.8069 - dense_1_loss_2: 1.5020 - dense_1_loss_3: 0.4839 - dense_1_loss_4: 0.1293 - dense_1_loss_5: 0.0888 - dense_1_loss_6: 0.0602 - dense_1_loss_7: 0.0463 - dense_1_loss_8: 0.0468 - dense_1_loss_9: 0.0406 - dense_1_loss_10: 0.0354 - dense_1_loss_11: 0.0383 - dense_1_loss_12: 0.0362 - dense_1_loss_13: 0.0335 - dense_1_loss_14: 0.0367 - dense_1_loss_15: 0.0368 - dense_1_loss_16: 0.0409 - dense_1_loss_17: 0.0364 - dense_1_loss_18: 0.0323 - dense_1_loss_19: 0.0327 - dense_1_loss_20: 0.0365 - dense_1_loss_21: 0.0356 - dense_1_loss_22: 0.0378 - dense_1_loss_23: 0.0354 - dense_1_loss_24: 0.0347 - dense_1_loss_25: 0.0414 - dense_1_loss_26: 0.0337 - dense_1_loss_27: 0.0340 - dense_1_loss_28: 0.0383 - dense_1_loss_29: 0.0383 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 84/100
60/60 [==============================] - 0s - loss: 6.8737 - dense_1_loss_1: 3.8042 - dense_1_loss_2: 1.4874 - dense_1_loss_3: 0.4752 - dense_1_loss_4: 0.1261 - dense_1_loss_5: 0.0864 - dense_1_loss_6: 0.0586 - dense_1_loss_7: 0.0451 - dense_1_loss_8: 0.0456 - dense_1_loss_9: 0.0395 - dense_1_loss_10: 0.0345 - dense_1_loss_11: 0.0372 - dense_1_loss_12: 0.0352 - dense_1_loss_13: 0.0326 - dense_1_loss_14: 0.0356 - dense_1_loss_15: 0.0358 - dense_1_loss_16: 0.0398 - dense_1_loss_17: 0.0354 - dense_1_loss_18: 0.0315 - dense_1_loss_19: 0.0318 - dense_1_loss_20: 0.0354 - dense_1_loss_21: 0.0348 - dense_1_loss_22: 0.0367 - dense_1_loss_23: 0.0346 - dense_1_loss_24: 0.0338 - dense_1_loss_25: 0.0402 - dense_1_loss_26: 0.0329 - dense_1_loss_27: 0.0331 - dense_1_loss_28: 0.0375 - dense_1_loss_29: 0.0373 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 85/100
60/60 [==============================] - 0s - loss: 6.8185 - dense_1_loss_1: 3.8013 - dense_1_loss_2: 1.4737 - dense_1_loss_3: 0.4658 - dense_1_loss_4: 0.1229 - dense_1_loss_5: 0.0841 - dense_1_loss_6: 0.0570 - dense_1_loss_7: 0.0438 - dense_1_loss_8: 0.0443 - dense_1_loss_9: 0.0385 - dense_1_loss_10: 0.0336 - dense_1_loss_11: 0.0361 - dense_1_loss_12: 0.0343 - dense_1_loss_13: 0.0318 - dense_1_loss_14: 0.0345 - dense_1_loss_15: 0.0348 - dense_1_loss_16: 0.0389 - dense_1_loss_17: 0.0345 - dense_1_loss_18: 0.0306 - dense_1_loss_19: 0.0309 - dense_1_loss_20: 0.0344 - dense_1_loss_21: 0.0339 - dense_1_loss_22: 0.0358 - dense_1_loss_23: 0.0337 - dense_1_loss_24: 0.0330 - dense_1_loss_25: 0.0390 - dense_1_loss_26: 0.0321 - dense_1_loss_27: 0.0324 - dense_1_loss_28: 0.0365 - dense_1_loss_29: 0.0363 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 86/100
60/60 [==============================] - 0s - loss: 6.7663 - dense_1_loss_1: 3.7987 - dense_1_loss_2: 1.4595 - dense_1_loss_3: 0.4575 - dense_1_loss_4: 0.1202 - dense_1_loss_5: 0.0820 - dense_1_loss_6: 0.0557 - dense_1_loss_7: 0.0427 - dense_1_loss_8: 0.0432 - dense_1_loss_9: 0.0374 - dense_1_loss_10: 0.0327 - dense_1_loss_11: 0.0352 - dense_1_loss_12: 0.0334 - dense_1_loss_13: 0.0309 - dense_1_loss_14: 0.0336 - dense_1_loss_15: 0.0340 - dense_1_loss_16: 0.0380 - dense_1_loss_17: 0.0336 - dense_1_loss_18: 0.0298 - dense_1_loss_19: 0.0301 - dense_1_loss_20: 0.0334 - dense_1_loss_21: 0.0330 - dense_1_loss_22: 0.0350 - dense_1_loss_23: 0.0329 - dense_1_loss_24: 0.0322 - dense_1_loss_25: 0.0380 - dense_1_loss_26: 0.0312 - dense_1_loss_27: 0.0317 - dense_1_loss_28: 0.0354 - dense_1_loss_29: 0.0354 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 87/100
60/60 [==============================] - 0s - loss: 6.7160 - dense_1_loss_1: 3.7956 - dense_1_loss_2: 1.4466 - dense_1_loss_3: 0.4495 - dense_1_loss_4: 0.1174 - dense_1_loss_5: 0.0800 - dense_1_loss_6: 0.0543 - dense_1_loss_7: 0.0417 - dense_1_loss_8: 0.0421 - dense_1_loss_9: 0.0366 - dense_1_loss_10: 0.0319 - dense_1_loss_11: 0.0343 - dense_1_loss_12: 0.0326 - dense_1_loss_13: 0.0302 - dense_1_loss_14: 0.0326 - dense_1_loss_15: 0.0332 - dense_1_loss_16: 0.0370 - dense_1_loss_17: 0.0327 - dense_1_loss_18: 0.0290 - dense_1_loss_19: 0.0294 - dense_1_loss_20: 0.0325 - dense_1_loss_21: 0.0322 - dense_1_loss_22: 0.0341 - dense_1_loss_23: 0.0320 - dense_1_loss_24: 0.0313 - dense_1_loss_25: 0.0370 - dense_1_loss_26: 0.0303 - dense_1_loss_27: 0.0308 - dense_1_loss_28: 0.0345 - dense_1_loss_29: 0.0345 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 88/100
60/60 [==============================] - 0s - loss: 6.6662 - dense_1_loss_1: 3.7928 - dense_1_loss_2: 1.4330 - dense_1_loss_3: 0.4411 - dense_1_loss_4: 0.1149 - dense_1_loss_5: 0.0780 - dense_1_loss_6: 0.0531 - dense_1_loss_7: 0.0406 - dense_1_loss_8: 0.0411 - dense_1_loss_9: 0.0357 - dense_1_loss_10: 0.0312 - dense_1_loss_11: 0.0335 - dense_1_loss_12: 0.0318 - dense_1_loss_13: 0.0294 - dense_1_loss_14: 0.0318 - dense_1_loss_15: 0.0324 - dense_1_loss_16: 0.0361 - dense_1_loss_17: 0.0319 - dense_1_loss_18: 0.0283 - dense_1_loss_19: 0.0286 - dense_1_loss_20: 0.0318 - dense_1_loss_21: 0.0313 - dense_1_loss_22: 0.0332 - dense_1_loss_23: 0.0312 - dense_1_loss_24: 0.0305 - dense_1_loss_25: 0.0362 - dense_1_loss_26: 0.0294 - dense_1_loss_27: 0.0300 - dense_1_loss_28: 0.0336 - dense_1_loss_29: 0.0336 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 89/100
60/60 [==============================] - 0s - loss: 6.6180 - dense_1_loss_1: 3.7900 - dense_1_loss_2: 1.4197 - dense_1_loss_3: 0.4333 - dense_1_loss_4: 0.1120 - dense_1_loss_5: 0.0761 - dense_1_loss_6: 0.0518 - dense_1_loss_7: 0.0396 - dense_1_loss_8: 0.0401 - dense_1_loss_9: 0.0348 - dense_1_loss_10: 0.0304 - dense_1_loss_11: 0.0327 - dense_1_loss_12: 0.0311 - dense_1_loss_13: 0.0287 - dense_1_loss_14: 0.0310 - dense_1_loss_15: 0.0317 - dense_1_loss_16: 0.0352 - dense_1_loss_17: 0.0311 - dense_1_loss_18: 0.0276 - dense_1_loss_19: 0.0278 - dense_1_loss_20: 0.0312 - dense_1_loss_21: 0.0305 - dense_1_loss_22: 0.0324 - dense_1_loss_23: 0.0304 - dense_1_loss_24: 0.0298 - dense_1_loss_25: 0.0354 - dense_1_loss_26: 0.0287 - dense_1_loss_27: 0.0293 - dense_1_loss_28: 0.0329 - dense_1_loss_29: 0.0328 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 90/100
60/60 [==============================] - 0s - loss: 6.5729 - dense_1_loss_1: 3.7873 - dense_1_loss_2: 1.4072 - dense_1_loss_3: 0.4260 - dense_1_loss_4: 0.1095 - dense_1_loss_5: 0.0744 - dense_1_loss_6: 0.0506 - dense_1_loss_7: 0.0386 - dense_1_loss_8: 0.0393 - dense_1_loss_9: 0.0339 - dense_1_loss_10: 0.0297 - dense_1_loss_11: 0.0319 - dense_1_loss_12: 0.0303 - dense_1_loss_13: 0.0280 - dense_1_loss_14: 0.0303 - dense_1_loss_15: 0.0310 - dense_1_loss_16: 0.0343 - dense_1_loss_17: 0.0302 - dense_1_loss_18: 0.0270 - dense_1_loss_19: 0.0272 - dense_1_loss_20: 0.0305 - dense_1_loss_21: 0.0297 - dense_1_loss_22: 0.0317 - dense_1_loss_23: 0.0297 - dense_1_loss_24: 0.0292 - dense_1_loss_25: 0.0346 - dense_1_loss_26: 0.0281 - dense_1_loss_27: 0.0286 - dense_1_loss_28: 0.0322 - dense_1_loss_29: 0.0320 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 91/100
60/60 [==============================] - 0s - loss: 6.5286 - dense_1_loss_1: 3.7847 - dense_1_loss_2: 1.3945 - dense_1_loss_3: 0.4191 - dense_1_loss_4: 0.1070 - dense_1_loss_5: 0.0728 - dense_1_loss_6: 0.0494 - dense_1_loss_7: 0.0377 - dense_1_loss_8: 0.0384 - dense_1_loss_9: 0.0331 - dense_1_loss_10: 0.0290 - dense_1_loss_11: 0.0311 - dense_1_loss_12: 0.0296 - dense_1_loss_13: 0.0273 - dense_1_loss_14: 0.0295 - dense_1_loss_15: 0.0303 - dense_1_loss_16: 0.0335 - dense_1_loss_17: 0.0296 - dense_1_loss_18: 0.0264 - dense_1_loss_19: 0.0265 - dense_1_loss_20: 0.0298 - dense_1_loss_21: 0.0290 - dense_1_loss_22: 0.0309 - dense_1_loss_23: 0.0290 - dense_1_loss_24: 0.0285 - dense_1_loss_25: 0.0337 - dense_1_loss_26: 0.0275 - dense_1_loss_27: 0.0279 - dense_1_loss_28: 0.0315 - dense_1_loss_29: 0.0313 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 92/100
60/60 [==============================] - 0s - loss: 6.4846 - dense_1_loss_1: 3.7818 - dense_1_loss_2: 1.3821 - dense_1_loss_3: 0.4118 - dense_1_loss_4: 0.1046 - dense_1_loss_5: 0.0712 - dense_1_loss_6: 0.0483 - dense_1_loss_7: 0.0368 - dense_1_loss_8: 0.0375 - dense_1_loss_9: 0.0323 - dense_1_loss_10: 0.0284 - dense_1_loss_11: 0.0304 - dense_1_loss_12: 0.0289 - dense_1_loss_13: 0.0267 - dense_1_loss_14: 0.0288 - dense_1_loss_15: 0.0296 - dense_1_loss_16: 0.0327 - dense_1_loss_17: 0.0289 - dense_1_loss_18: 0.0258 - dense_1_loss_19: 0.0259 - dense_1_loss_20: 0.0290 - dense_1_loss_21: 0.0283 - dense_1_loss_22: 0.0303 - dense_1_loss_23: 0.0284 - dense_1_loss_24: 0.0278 - dense_1_loss_25: 0.0329 - dense_1_loss_26: 0.0269 - dense_1_loss_27: 0.0273 - dense_1_loss_28: 0.0307 - dense_1_loss_29: 0.0305 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 93/100
60/60 [==============================] - 0s - loss: 6.4439 - dense_1_loss_1: 3.7790 - dense_1_loss_2: 1.3704 - dense_1_loss_3: 0.4051 - dense_1_loss_4: 0.1026 - dense_1_loss_5: 0.0696 - dense_1_loss_6: 0.0473 - dense_1_loss_7: 0.0360 - dense_1_loss_8: 0.0367 - dense_1_loss_9: 0.0316 - dense_1_loss_10: 0.0278 - dense_1_loss_11: 0.0297 - dense_1_loss_12: 0.0283 - dense_1_loss_13: 0.0262 - dense_1_loss_14: 0.0281 - dense_1_loss_15: 0.0290 - dense_1_loss_16: 0.0320 - dense_1_loss_17: 0.0283 - dense_1_loss_18: 0.0252 - dense_1_loss_19: 0.0254 - dense_1_loss_20: 0.0282 - dense_1_loss_21: 0.0277 - dense_1_loss_22: 0.0297 - dense_1_loss_23: 0.0278 - dense_1_loss_24: 0.0272 - dense_1_loss_25: 0.0322 - dense_1_loss_26: 0.0263 - dense_1_loss_27: 0.0267 - dense_1_loss_28: 0.0299 - dense_1_loss_29: 0.0299 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 94/100
60/60 [==============================] - 0s - loss: 6.4034 - dense_1_loss_1: 3.7766 - dense_1_loss_2: 1.3584 - dense_1_loss_3: 0.3977 - dense_1_loss_4: 0.1008 - dense_1_loss_5: 0.0681 - dense_1_loss_6: 0.0464 - dense_1_loss_7: 0.0353 - dense_1_loss_8: 0.0359 - dense_1_loss_9: 0.0308 - dense_1_loss_10: 0.0272 - dense_1_loss_11: 0.0291 - dense_1_loss_12: 0.0277 - dense_1_loss_13: 0.0256 - dense_1_loss_14: 0.0274 - dense_1_loss_15: 0.0284 - dense_1_loss_16: 0.0313 - dense_1_loss_17: 0.0277 - dense_1_loss_18: 0.0246 - dense_1_loss_19: 0.0248 - dense_1_loss_20: 0.0276 - dense_1_loss_21: 0.0271 - dense_1_loss_22: 0.0290 - dense_1_loss_23: 0.0272 - dense_1_loss_24: 0.0266 - dense_1_loss_25: 0.0315 - dense_1_loss_26: 0.0257 - dense_1_loss_27: 0.0262 - dense_1_loss_28: 0.0293 - dense_1_loss_29: 0.0293 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 95/100
60/60 [==============================] - ETA: 0s - loss: 6.2866 - dense_1_loss_1: 3.8300 - dense_1_loss_2: 1.2974 - dense_1_loss_3: 0.3257 - dense_1_loss_4: 0.0788 - dense_1_loss_5: 0.0600 - dense_1_loss_6: 0.0385 - dense_1_loss_7: 0.0346 - dense_1_loss_8: 0.0326 - dense_1_loss_9: 0.0293 - dense_1_loss_10: 0.0267 - dense_1_loss_11: 0.0262 - dense_1_loss_12: 0.0272 - dense_1_loss_13: 0.0251 - dense_1_loss_14: 0.0261 - dense_1_loss_15: 0.0284 - dense_1_loss_16: 0.0285 - dense_1_loss_17: 0.0270 - dense_1_loss_18: 0.0249 - dense_1_loss_19: 0.0245 - dense_1_loss_20: 0.0270 - dense_1_loss_21: 0.0281 - dense_1_loss_22: 0.0304 - dense_1_loss_23: 0.0266 - dense_1_loss_24: 0.0265 - dense_1_loss_25: 0.0334 - dense_1_loss_26: 0.0285 - dense_1_loss_27: 0.0261 - dense_1_loss_28: 0.0339 - dense_1_loss_29: 0.0348 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0312 - dense_1_acc_2: 0.6250 - dense_1_acc_3: 0.9375 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+0 - 0s - loss: 6.3636 - dense_1_loss_1: 3.7738 - dense_1_loss_2: 1.3471 - dense_1_loss_3: 0.3905 - dense_1_loss_4: 0.0989 - dense_1_loss_5: 0.0667 - dense_1_loss_6: 0.0453 - dense_1_loss_7: 0.0345 - dense_1_loss_8: 0.0351 - dense_1_loss_9: 0.0301 - dense_1_loss_10: 0.0266 - dense_1_loss_11: 0.0285 - dense_1_loss_12: 0.0271 - dense_1_loss_13: 0.0250 - dense_1_loss_14: 0.0268 - dense_1_loss_15: 0.0278 - dense_1_loss_16: 0.0307 - dense_1_loss_17: 0.0270 - dense_1_loss_18: 0.0241 - dense_1_loss_19: 0.0242 - dense_1_loss_20: 0.0271 - dense_1_loss_21: 0.0265 - dense_1_loss_22: 0.0284 - dense_1_loss_23: 0.0266 - dense_1_loss_24: 0.0260 - dense_1_loss_25: 0.0309 - dense_1_loss_26: 0.0252 - dense_1_loss_27: 0.0256 - dense_1_loss_28: 0.0288 - dense_1_loss_29: 0.0288 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 96/100
60/60 [==============================] - 0s - loss: 6.3253 - dense_1_loss_1: 3.7711 - dense_1_loss_2: 1.3354 - dense_1_loss_3: 0.3842 - dense_1_loss_4: 0.0971 - dense_1_loss_5: 0.0654 - dense_1_loss_6: 0.0445 - dense_1_loss_7: 0.0337 - dense_1_loss_8: 0.0344 - dense_1_loss_9: 0.0295 - dense_1_loss_10: 0.0260 - dense_1_loss_11: 0.0280 - dense_1_loss_12: 0.0265 - dense_1_loss_13: 0.0244 - dense_1_loss_14: 0.0264 - dense_1_loss_15: 0.0271 - dense_1_loss_16: 0.0300 - dense_1_loss_17: 0.0264 - dense_1_loss_18: 0.0236 - dense_1_loss_19: 0.0237 - dense_1_loss_20: 0.0266 - dense_1_loss_21: 0.0259 - dense_1_loss_22: 0.0277 - dense_1_loss_23: 0.0260 - dense_1_loss_24: 0.0255 - dense_1_loss_25: 0.0302 - dense_1_loss_26: 0.0246 - dense_1_loss_27: 0.0251 - dense_1_loss_28: 0.0282 - dense_1_loss_29: 0.0281 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 97/100
60/60 [==============================] - 0s - loss: 6.2876 - dense_1_loss_1: 3.7685 - dense_1_loss_2: 1.3240 - dense_1_loss_3: 0.3778 - dense_1_loss_4: 0.0952 - dense_1_loss_5: 0.0640 - dense_1_loss_6: 0.0436 - dense_1_loss_7: 0.0329 - dense_1_loss_8: 0.0336 - dense_1_loss_9: 0.0289 - dense_1_loss_10: 0.0255 - dense_1_loss_11: 0.0274 - dense_1_loss_12: 0.0259 - dense_1_loss_13: 0.0238 - dense_1_loss_14: 0.0258 - dense_1_loss_15: 0.0265 - dense_1_loss_16: 0.0294 - dense_1_loss_17: 0.0259 - dense_1_loss_18: 0.0231 - dense_1_loss_19: 0.0232 - dense_1_loss_20: 0.0260 - dense_1_loss_21: 0.0254 - dense_1_loss_22: 0.0272 - dense_1_loss_23: 0.0254 - dense_1_loss_24: 0.0250 - dense_1_loss_25: 0.0295 - dense_1_loss_26: 0.0241 - dense_1_loss_27: 0.0246 - dense_1_loss_28: 0.0277 - dense_1_loss_29: 0.0275 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 98/100
60/60 [==============================] - 0s - loss: 6.2525 - dense_1_loss_1: 3.7658 - dense_1_loss_2: 1.3135 - dense_1_loss_3: 0.3719 - dense_1_loss_4: 0.0933 - dense_1_loss_5: 0.0628 - dense_1_loss_6: 0.0428 - dense_1_loss_7: 0.0323 - dense_1_loss_8: 0.0329 - dense_1_loss_9: 0.0284 - dense_1_loss_10: 0.0249 - dense_1_loss_11: 0.0269 - dense_1_loss_12: 0.0254 - dense_1_loss_13: 0.0233 - dense_1_loss_14: 0.0254 - dense_1_loss_15: 0.0259 - dense_1_loss_16: 0.0288 - dense_1_loss_17: 0.0253 - dense_1_loss_18: 0.0227 - dense_1_loss_19: 0.0228 - dense_1_loss_20: 0.0255 - dense_1_loss_21: 0.0249 - dense_1_loss_22: 0.0267 - dense_1_loss_23: 0.0249 - dense_1_loss_24: 0.0245 - dense_1_loss_25: 0.0289 - dense_1_loss_26: 0.0237 - dense_1_loss_27: 0.0241 - dense_1_loss_28: 0.0271 - dense_1_loss_29: 0.0270 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 99/100
60/60 [==============================] - 0s - loss: 6.2174 - dense_1_loss_1: 3.7632 - dense_1_loss_2: 1.3026 - dense_1_loss_3: 0.3658 - dense_1_loss_4: 0.0918 - dense_1_loss_5: 0.0617 - dense_1_loss_6: 0.0420 - dense_1_loss_7: 0.0317 - dense_1_loss_8: 0.0323 - dense_1_loss_9: 0.0278 - dense_1_loss_10: 0.0245 - dense_1_loss_11: 0.0262 - dense_1_loss_12: 0.0249 - dense_1_loss_13: 0.0229 - dense_1_loss_14: 0.0247 - dense_1_loss_15: 0.0254 - dense_1_loss_16: 0.0282 - dense_1_loss_17: 0.0248 - dense_1_loss_18: 0.0222 - dense_1_loss_19: 0.0223 - dense_1_loss_20: 0.0250 - dense_1_loss_21: 0.0244 - dense_1_loss_22: 0.0261 - dense_1_loss_23: 0.0245 - dense_1_loss_24: 0.0241 - dense_1_loss_25: 0.0283 - dense_1_loss_26: 0.0232 - dense_1_loss_27: 0.0237 - dense_1_loss_28: 0.0265 - dense_1_loss_29: 0.0265 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6333 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
Epoch 100/100
60/60 [==============================] - 0s - loss: 6.1834 - dense_1_loss_1: 3.7607 - dense_1_loss_2: 1.2922 - dense_1_loss_3: 0.3598 - dense_1_loss_4: 0.0903 - dense_1_loss_5: 0.0606 - dense_1_loss_6: 0.0412 - dense_1_loss_7: 0.0311 - dense_1_loss_8: 0.0317 - dense_1_loss_9: 0.0272 - dense_1_loss_10: 0.0240 - dense_1_loss_11: 0.0257 - dense_1_loss_12: 0.0244 - dense_1_loss_13: 0.0224 - dense_1_loss_14: 0.0242 - dense_1_loss_15: 0.0250 - dense_1_loss_16: 0.0277 - dense_1_loss_17: 0.0244 - dense_1_loss_18: 0.0218 - dense_1_loss_19: 0.0219 - dense_1_loss_20: 0.0244 - dense_1_loss_21: 0.0240 - dense_1_loss_22: 0.0256 - dense_1_loss_23: 0.0240 - dense_1_loss_24: 0.0236 - dense_1_loss_25: 0.0278 - dense_1_loss_26: 0.0227 - dense_1_loss_27: 0.0233 - dense_1_loss_28: 0.0260 - dense_1_loss_29: 0.0260 - dense_1_loss_30: 0.0000e+00 - dense_1_acc_1: 0.0667 - dense_1_acc_2: 0.6500 - dense_1_acc_3: 0.9000 - dense_1_acc_4: 1.0000 - dense_1_acc_5: 1.0000 - dense_1_acc_6: 1.0000 - dense_1_acc_7: 1.0000 - dense_1_acc_8: 1.0000 - dense_1_acc_9: 1.0000 - dense_1_acc_10: 1.0000 - dense_1_acc_11: 1.0000 - dense_1_acc_12: 1.0000 - dense_1_acc_13: 1.0000 - dense_1_acc_14: 1.0000 - dense_1_acc_15: 1.0000 - dense_1_acc_16: 1.0000 - dense_1_acc_17: 1.0000 - dense_1_acc_18: 1.0000 - dense_1_acc_19: 1.0000 - dense_1_acc_20: 1.0000 - dense_1_acc_21: 1.0000 - dense_1_acc_22: 1.0000 - dense_1_acc_23: 1.0000 - dense_1_acc_24: 1.0000 - dense_1_acc_25: 1.0000 - dense_1_acc_26: 1.0000 - dense_1_acc_27: 1.0000 - dense_1_acc_28: 1.0000 - dense_1_acc_29: 1.0000 - dense_1_acc_30: 0.0000e+00     
<keras.callbacks.History at 0x7ff15e2f6978>

You should see the model loss going down. Now that you have trained a model, lets go on the the final section to implement an inference algorithm, and generate some music!　　

 

3 - Generating music

You now have a trained model which has learned the patterns of the jazz soloist. Lets now use this model to synthesize new music.

3.1 - Predicting & Sampling

At each step of sampling, you will take as input the activation a and cell state c from the previous state of the LSTM, forward propagate by one step, and get a new output activation as well as cell state. The new activation a can then be used to generate the output, using densor as before.

To start off the model, we will initialize x0 as well as the LSTM activation and and cell value a0 and c0 to be zeros.

Exercise: Implement the function below to sample a sequence of musical values. Here are some of the key steps you'll need to implement inside the for-loop that generates the Ty output characters:

Step 2.A: Use LSTM_Cell, which inputs the previous step's c and a to generate the current step's c and a.

Step 2.B: Use densor (defined previously) to compute a softmax on a to get the output for the current step.

Step 2.C: Save the output you have just generated by appending it to outputs.

Step 2.D: Sample x to the be "out"'s one-hot version (the prediction) so that you can pass it to the next LSTM's step. We have already provided this line of code, which uses a Lambda function.

x = Lambda(one_hot)(out)

[Minor technical note: Rather than sampling a value at random according to the probabilities in out, this line of code actually chooses the single most likely note at each step using an argmax.]

【中文翻译】

练习: 执行下面的函数来取样一个音乐值序列。以下是在生成 Ty 输出字符的 for 循环内需要实现的一些关键步骤:
步骤 2.A: 使用 LSTM_Cell, 它输入上一步的 c 和 a 以生成当前步骤的 c 和 a。
步骤 2.B: 使用 densor (先前定义) 在 a 上计算 softmax 以获取当前步骤的输出。
步骤 2.C: 通过将刚刚生成的输出追加到输出中来保存。
步骤 2.D: 采样 x 到 "out" 的一个one-hot本 (即预测值), 以便您可以将其传递到下一个 LSTM 的步骤。我们已经提供了这行代码, 它使用 Lambda 函数。
x = Lambda(one_hot)(out)
 
[次要技术说明: 不是根据概率随机抽样值, 这行代码实际上在每个步骤中使用 argmax 来选择一个最可能的值。

【code】

# GRADED FUNCTION: music_inference_model

def music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 100):
    """
    Uses the trained "LSTM_cell" and "densor" from model() to generate a sequence of values.
    
    Arguments:
    LSTM_cell -- the trained "LSTM_cell" from model(), Keras layer object
    densor -- the trained "densor" from model(), Keras layer object
    n_values -- integer, umber of unique values
    n_a -- number of units in the LSTM_cell
    Ty -- integer, number of time steps to generate
    
    Returns:
    inference_model -- Keras model instance
    """
    
    # Define the input of your model with a shape 
    x0 = Input(shape=(1, n_values))
    
    # Define s0, initial hidden state for the decoder LSTM
    a0 = Input(shape=(n_a,), name='a0')
    c0 = Input(shape=(n_a,), name='c0')
    a = a0
    c = c0
    x = x0

    ### START CODE HERE ###
    # Step 1: Create an empty list of "outputs" to later store your predicted values (≈1 line)
    outputs = []
    
    # Step 2: Loop over Ty and generate a value at every time step
    for t in range(Ty):
        
        # Step 2.A: Perform one step of LSTM_cell (≈1 line)
        a, _, c = LSTM_cell(x, initial_state=[a, c])
        
        # Step 2.B: Apply Dense layer to the hidden state output of the LSTM_cell (≈1 line)
        out = densor(a)

        # Step 2.C: Append the prediction "out" to "outputs". out.shape = (None, 78) (≈1 line)
        outputs.append(out)
        
        # Step 2.D: Select the next value according to "out", and set "x" to be the one-hot representation of the
        #           selected value, which will be passed as the input to LSTM_cell on the next step. We have provided 
        #           the line of code you need to do this. 
        x = Lambda(one_hot)(out)
        
    # Step 3: Create model instance with the correct "inputs" and "outputs" (≈1 line)
    inference_model =  Model([x0, a0, c0], outputs)
    
    ### END CODE HERE ###
    
    return inference_model

Run the cell below to define your inference model. This model is hard coded to generate 50 values.　　

【code】

inference_model = music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 50)

Finally, this creates the zero-valued vectors you will use to initialize x and the LSTM state variables a and c.　

【code】　

x_initializer = np.zeros((1, 1, 78))
a_initializer = np.zeros((1, n_a))
c_initializer = np.zeros((1, n_a))

　　

Exercise: Implement predict_and_sample(). This function takes many arguments including the inputs [x_initializer, a_initializer, c_initializer]. In order to predict the output corresponding to this input, you will need to carry-out 3 steps:

  1. Use your inference model to predict an output given your set of inputs. The output pred should be a list of length Ty where each element is a numpy-array of shape (1, n_values).
  2. Convert pred into a numpy array of Ty indices. Each index corresponds is computed by taking the argmax of an element of the pred list. Hint.
  3. Convert the indices into their one-hot vector representations. Hint.

【code】

# GRADED FUNCTION: predict_and_sample

def predict_and_sample(inference_model, x_initializer = x_initializer, a_initializer = a_initializer, 
                       c_initializer = c_initializer):
    """
    Predicts the next value of values using the inference model.
    
    Arguments:
    inference_model -- Keras model instance for inference time
    x_initializer -- numpy array of shape (1, 1, 78), one-hot vector initializing the values generation
    a_initializer -- numpy array of shape (1, n_a), initializing the hidden state of the LSTM_cell
    c_initializer -- numpy array of shape (1, n_a), initializing the cell state of the LSTM_cel
    
    Returns:
    results -- numpy-array of shape (Ty, 78), matrix of one-hot vectors representing the values generated
    indices -- numpy-array of shape (Ty, 1), matrix of indices representing the values generated
    """
    
    ### START CODE HERE ###
    # Step 1: Use your inference model to predict an output sequence given x_initializer, a_initializer and c_initializer.
    pred = inference_model.predict([x_initializer, a_initializer, c_initializer])
    # Step 2: Convert "pred" into an np.array() of indices with the maximum probabilities
    indices = np.argmax(pred,axis=2)
    # Step 3: Convert indices to one-hot vectors, the shape of the results should be (1, )
    results = to_categorical(indices)
    ### END CODE HERE ###
    
    return results, indices

results, indices = predict_and_sample(inference_model, x_initializer, a_initializer, c_initializer)
print("np.argmax(results[12]) =", np.argmax(results[12]))
print("np.argmax(results[17]) =", np.argmax(results[17]))
print("list(indices[12:18]) =", list(indices[12:18]))

　　

【result】　　

np.argmax(results[12]) = 22
np.argmax(results[17]) = 59
list(indices[12:18]) = [array([22]), array([33]), array([50]), array([67]), array([77]), array([59])]

　　

 【Expected Output】

 Your results may differ because Keras' results are not completely predictable. However, if you have trained your LSTM_cell with model.fit() for exactly 100 epochs as described above, you should very likely observe a sequence of indices that are not all identical. Moreover, you should observe that: np.argmax(results[12]) is the first element of list(indices[12:18]) and np.argmax(results[17]) is the last element of list(indices[12:18]).

np.argmax(results[12]) =	1
np.argmax(results[12]) =	42
list(indices[12:18]) =	[array([1]), array([42]), array([54]), array([17]), array([1]), array([42])]

　　

3.3 - Generate music

Finally, you are ready to generate music. Your RNN generates a sequence of values. The following code generates music by first calling your predict_and_sample() function. These values are then post-processed into musical chords (meaning that multiple values or notes can be played at the same time).

Most computational music algorithms use some post-processing because it is difficult to generate music that sounds good without such post-processing. The post-processing does things such as clean up the generated audio by making sure the same sound is not repeated too many times, that two successive notes are not too far from each other in pitch, and so on. One could argue that a lot of these post-processing steps are hacks; also, a lot the music generation literature has also focused on hand-crafting post-processors, and a lot of the output quality depends on the quality of the post-processing and not just the quality of the RNN. But this post-processing does make a huge difference, so lets use it in our implementation as well.

Lets make some music!

Run the following cell to generate music and record it into your out_stream. This can take a couple of minutes. 

【code】 

out_stream = generate_music(inference_model)

【result】

Predicting new values for different set of chords.
Generated 51 sounds using the predicted values for the set of chords ("1") and after pruning
Generated 50 sounds using the predicted values for the set of chords ("2") and after pruning
Generated 50 sounds using the predicted values for the set of chords ("3") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("4") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("5") and after pruning
Your generated music is saved in output/my_music.midi

To listen to your music, click File->Open... Then go to "output/" and download "my_music.midi". Either play it on your computer with an application that can read midi files if you have one, or use one of the free online "MIDI to mp3" conversion tools to convert this to mp3.

As reference, here also is a 30sec audio clip we generated using this algorithm.

【code】

IPython.display.Audio('./data/30s_trained_model.mp3')

【result】　　

注：原网页是一段音频，这里是截图

　　

Congratulations!

You have come to the end of the notebook.

Here's what you should remember:

  • A sequence model can be used to generate musical values, which are then post-processed into midi music.
  • Fairly similar models can be used to generate dinosaur names or to generate music, with the major difference being the input fed to the model.
  • In Keras, sequence generation involves defining layers with shared weights, which are then repeated for the different time steps 1,…,Tx.

Congratulations on completing this assignment and generating a jazz solo!

 

References

The ideas presented in this notebook came primarily from three computational music papers cited below. The implementation here also took significant inspiration and used many components from Ji-Sung Kim's github repository.

We're also grateful to François Germain for valuable feedback.

【推广】 免费学中医，健康全家人
原文地址：https://www.cnblogs.com/hezhiyao/p/8488897.html