深度学习实验项目一手写识别

项目参考唐老师手写识别项目及数据集。

数据集是：mnist-demo.csv

具体的实验步骤：

1.读取数据集文件，shape为：(10000, 785)，样式为：

进行one-hot编码，将Label转化成：

import pandas as pd 
import numpy as np
data=pd.read_csv("mnist-demo.csv")
label=pd.get_dummies(data["label"])
X=data.iloc[0:,1:]
Y=label

2.使用Keras进行训练测试

from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D
from tensorflow.keras import Input
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
from tensorflow.keras.regularizers import l1

model = Sequential()
# 第一个卷积层，32个卷积核，大小５x5，卷积模式SAME,激活函数relu,输入张量的大小
# model.add(Conv2D(filters= 6, kernel_size=(3,3), padding='valid',kernel_regularizer=l1(0.1),activation='tanh',input_shape=(128,128,3)))
# # model.add(Conv2D(filters= 32, kernel_size=(3,3), padding='valid', activation='relu'))
# # 池化层,池化核大小２x2
# model.add(MaxPool2D(pool_size=(2,2)))
# # 随机丢弃四分之一的网络连接，防止过拟合
# model.add(Dropout(0.5)) 
# model.add(Conv2D(filters= 6, kernel_size=(3,3), padding='Same', activation='tanh'))
# # model.add(Conv2D(filters= 6, kernel_size=(3,3), padding='Same', activation='tanh'))
# model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# model.add(Dropout(0.5))
# # 全连接层,展开操作，
# model.add(Flatten())
# 添加隐藏层神经元的数量和激活函数
model.add(Dense(120, activation='tanh',input_shape=(784,)))   
model.add(Dense(84, activation='tanh'))   
# 输出层
model.add(Dense(10, activation='softmax'))

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

model.fit(X,Y,validation_split=0.2,batch_size=100,epochs=50)

训练结果如下：