前言
Tensorflow的eager模式是一个命令式编程环境,它使得我们可以立即评估操作产生的结果,而无需构建计算图。
图运算需要搭建好整个框架,再把东西倒进去才能生出结果,过程中是看不到里面的运作。
eager模式极大的方便了我们使用Tensorflow、调试模型,增加了网络调试的灵活程度和Tensorflow对于初学者的友好性,亦称为Tensorflow的交互模式。
与Tensorflow 1.x版本不同,Tensorflow 2.0默认使用eager模式,执行tf.executing_eagerly(),返回True。
编译环境
Tensorflow2.0
Python 3.6.12
Cuda 10.0.13
cuDNN 7.6.5
eager模式的优点:
1.提供了一个灵活的研究和实验机器学习平台。
2.提供了一个直观的界面,自然地构建代码并使用Python数据结构,快速迭代小型模型和小型数据。
3.更容易调试,在交互式环境中直接检查、运行模型、测试变化,这个过程中代码会及时报错。
4.可以使用自然地控制流,是python的控制流而不是图控制流,热切执行支持大多数Tensorflow操作和GPU加速。eager模式下,Tensorflow操作会立即执行并将其值返回给python,tf.Tensor对象引用具体值而不是计算图中节点的符号句柄。
5.eager模式下Tensorflow可与Numpy很好地协作,Tensorflow数学运算可将Python对象和Numpy数组转换为tf.Tensor对象,而tf.Tensor.numpy方法将对象的值作为Numpy返回ndarry。
eager模式下的代码
import tensorflow as tf print(tf.executing_eagerly()) # True
x = [[2,]] m = tf.matmul(x,x) #矩阵相乘 print(m) #tf.Tensor([[4]], shape=(1, 1), dtype=int32) #Tensor->numpy print(m.numpy(),type(m.numpy())) # [[4]] <class 'numpy.ndarray'> #建立一个常量 a = tf.constant([[1,2],[3,4]]) print(a) # tf.Tensor( # [[1 2] # [3 4]], shape=(2, 2), dtype=int32) print(a.numpy()) # [[1 2] # [3 4]] #相加 print(tf.add(a,1).numpy()) # [[2 3] # [4 5]] #乘法 print(tf.multiply(a,2).numpy()) # [[2 4] # [6 8]] #利用python控制流写tensorflow的运算 num = tf.convert_to_tensor(10) for i in range(num.numpy()): i = tf.constant(i) if int(i) % 2 == 0: print("even") else: print("odd") # even # odd # even # odd # even # odd # even # odd # even # odd #与numpy协作运算 import numpy as np a1 = np.array([[1,2], [3,4]]) b1 = tf.constant([[1,5], [7,4]]) print(a1 + b1,type(a1 + b1),(a1 + b1).dtype) # tf.Tensor( # [[ 2 7] # [10 8]], shape=(2, 2), dtype=int32) <class 'tensorflow.python.framework.ops.EagerTensor'> <dtype: 'int32'> f = tf.convert_to_tensor(2.0) print(float(f)) # 2.0
变量
import tensorflow as tf #创建一个变量,主要运用与梯度下降去改变这些变量 v = tf.Variable(0.0) print(v + 1,(v + 1).numpy()) # tf.Tensor(1.0, shape=(), dtype=float32) 1.0 #直接改变变量的值 v.assign(5.0) print(v) # <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=5.0> #可以每次增加变量的值 for i in range(tf.constant(3).numpy()): v.assign_add(1.0) print(v) # <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=6.0> # <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=7.0> # <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=8.0> #可以每次减去变量的值 v.assign_sub(3) print(v) # <tf.Variable 'Variable:0' shape=() dtype=float32, numpy=5.0> #读取变量的值 print(v.read_value()) # tf.Tensor(5.0, shape=(), dtype=float32)
自动微分运算
import tensorflow as tf #tape(磁带) 去记录我们梯度的一个过程，会自动跟踪变量运算 w = tf.Variable([[1.0]]) with tf.GradientTape() as t: loss = w * w #损失函数 grad = t.gradient(loss,w) #梯度就是Loss对w进行求导 print(grad.numpy()) # [[2.]] w2 = tf.constant(3.0) with tf.GradientTape() as t2: t2.watch(w2) #让t去跟踪这个常量的运算 loss2 = w2 * w2 #损失函数 dloss_dw = t2.gradient(loss2,w2) #梯度就是Loss对w进行求导 print(dloss_dw.numpy()) # 6.0
#添加参数persistant可以永久计算参数 w = tf.constant(4.0) with tf.GradientTape(persistent=True) as t: t.watch(w) y = w * w z = y * y dy_dw = t.gradient(y,w) print(dy_dw.numpy()) #8.0 dz_dy = t.gradient(z,y) #出现RunTimeError说明tape它立即释放,不保留 print(dz_dy.numpy()) #32.0
自定义训练(MNIST数据集)
import tensorflow as tf from tensorflow.keras import layers,optimizers,losses (train_image,train_label),(test_image,test_label) = tf.keras.datasets.mnist.load_data() #扩大维度 print(train_image.shape) # (60000, 28, 28) train_image = tf.expand_dims(train_image,-1) train_image = tf.cast(train_image/255,tf.float32) test_iamge = tf.expand_dims(test_image,-1) test_image = tf.cast(test_image/255,tf.float32) train_label = tf.cast(train_label,tf.int64) test_label = tf.cast(test_label,tf.int64) dataset = tf.data.Dataset.from_tensor_slices((train_image,train_label)) test_dataset = tf.data.Dataset.from_tensor_slices((test_image,test_label)) BUFFER_SIZE = 10000 BATCH_SIZE = 32 dataset = dataset.shuffle(BUFFER_SIZE).repeat().batch(BATCH_SIZE) test_dataset = test_dataset.batch(BATCH_SIZE) model = tf.keras.Sequential() #如果要添加任意形状的shape可以(None,None,1) model.add(layers.Conv2D(16,(3,3),input_shape=(28,28,1),activation='relu')) model.add(layers.Conv2D(32,(3,3),activation='relu')) model.add(layers.GlobalAveragePooling2D()) # model.add(layers.Dense(10,activation='softmax')) model.add(layers.Dense(10)) model.summary() optimizer = optimizers.Adam() loss_fuc = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True) #最后未激活 features,labels = next(iter(dataset)) predictions = model.predict(features) print(predictions.shape) # (32, 10) print(tf.argmax(predictions,1)) # tf.Tensor([3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3], shape=(32,), dtype=int64) train_loss = tf.keras.metrics.Mean(name='train_loss') train_acc = tf.keras.metrics.SparseCategoricalAccuracy(name='train_acc') test_loss = tf.keras.metrics.Mean(name='test_loss') test_acc = tf.keras.metrics.SparseCategoricalAccuracy(name='test_acc') #自定义训练 def loss(model,x,y): #计算损失值,y表示实际的label,y_表示预测的label y_ = model(x) return loss_fuc(y,y_) #批次训练过程 def train_step(model,images,labels): with tf.GradientTape() as t: pred = model(images) #得到预测结果 loss_step = loss_fuc(labels,pred) #计算梯度 grads = t.gradient(loss_step,model.trainable_variables) #优化梯度 optimizer.apply_gradients(zip(grads,model.trainable_variables)) train_loss(loss_step) train_acc(labels,pred) def test_step(model,images,labels): pred = model(images) #得到预测结果 loss_step = loss_fuc(labels,pred) train_loss(loss_step) train_acc(labels,pred) EPOCH = 10 def train(): for epoch in range(EPOCH): for(batch,(images,labels)) in enumerate(dataset): train_step(model,images,labels) print('.',end='') print(' ') print('epoch{} loss is {},acc is {}'.format(epoch, train_loss.result(), train_acc.result())) for(batch,(images,labels)) in enumerate(test_dataset): test_step(model,images,labels) print('.',end='') print(' ') print('epoch{} loss is {},acc is {}'.format(epoch, test_loss.result(), test_acc.result())) #重置状态 train_loss.reset_states() train_acc.reset_states() test_loss.reset_states() test_acc.reset_states() train()
tf.keras.metrics模块
m = tf.keras.metrics.Mean('acc') print(m(10)) # tf.Tensor(10.0, shape=(), dtype=float32) print(m(20)) # tf.Tensor(15.0, shape=(), dtype=float32) print(m([10,10])) # tf.Tensor(12.5, shape=(), dtype=float32) print(m.result().numpy()) # 12.5 #重置状态 print(m.reset_states()) # None print(m(20)) # tf.Tensor(20.0, shape=(), dtype=float32)