tf.keras高层API自定义网络模板 (五) ---非常重要！！！

一、tf.keras.Layer类

自定义网络层
__init__，可以在其中 执行所有与输入无关的初始化
build方法，若知道输入张量的形状，并可以进行其余的初始化
call方法，在这里进行正向传播计算

在build()中创建网络结构是它可以根据图层将要操作的输入的形状启用后期的网络构建。但在__init__中创建变量，必须明确指定创建变量所需的形状。

class MyDense(layers.Layer):def __init__(self, inp_dim, outp_dim): # 参数：输入输出维度super(MyDense, self).__init__()    # 参数：与定义层的名字相对应# 自己定义的结构参数self.kernel = self.add_weight('w', [inp_dim, outp_dim])self.bias = self.add_weight('b', [outp_dim])def call(self, inputs, training=None):# 设置前向传播的连接方式out = inputs @ self.kernel + self.biasreturn out 

二、tf.keras.Model类

*创建一个包含多个网络层（tf.keras.Layer）的的结构。一般网络模型都是通过叠加不同的结构层组合而成的（比如卷积层、标准化层、残差连接等）。

class MyModel(keras.Model):def __init__(self):super(MyModel, self).__init__()# 初始化 不同的卷积层 layerself.fc1 = MyDense(28*28, 256)self.fc2 = MyDense(256, 128)self.fc3 = MyDense(128, 64)self.fc4 = MyDense(64, 32)self.fc5 = MyDense(32, 10)def call(self, inputs, training=None):# layer1x = self.fc1(inputs)x = tf.nn.relu(x)# layer2x = self.fc2(x)x = tf.nn.relu(x)# layer3x = self.fc3(x)x = tf.nn.relu(x)# layer4x = self.fc4(x)x = tf.nn.relu(x)# layer5x = self.fc5(x) return xnetwork = MyModel()  # 实例化

三、代码

import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from 	tensorflow import kerasdef preprocess(x, y):"""x is a simple image, not a batch"""x = tf.cast(x, dtype=tf.float32) / 255.x = tf.reshape(x, [28*28])y = tf.cast(y, dtype=tf.int32)y = tf.one_hot(y, depth=10)return x,ybatchsz = 128
(x, y), (x_val, y_val) = datasets.mnist.load_data()
print('datasets:', x.shape, y.shape, x.min(), x.max())db = tf.data.Dataset.from_tensor_slices((x,y))
db = db.map(preprocess).shuffle(60000).batch(batchsz)
ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
ds_val = ds_val.map(preprocess).batch(batchsz) sample = next(iter(db))
print(sample[0].shape, sample[1].shape)network = Sequential([layers.Dense(256, activation='relu'),layers.Dense(128, activation='relu'),layers.Dense(64, activation='relu'),layers.Dense(32, activation='relu'),layers.Dense(10)])
network.build(input_shape=(None, 28*28))
network.summary()class MyDense(layers.Layer):def __init__(self, inp_dim, outp_dim):super(MyDense, self).__init__()self.kernel = self.add_weight('w', [inp_dim, outp_dim])self.bias = self.add_weight('b', [outp_dim])def call(self, inputs, training=None):out = inputs @ self.kernel + self.biasreturn out class MyModel(keras.Model):def __init__(self):super(MyModel, self).__init__()self.fc1 = MyDense(28*28, 256)self.fc2 = MyDense(256, 128)self.fc3 = MyDense(128, 64)self.fc4 = MyDense(64, 32)self.fc5 = MyDense(32, 10)def call(self, inputs, training=None):x = self.fc1(inputs)x = tf.nn.relu(x)x = self.fc2(x)x = tf.nn.relu(x)x = self.fc3(x)x = tf.nn.relu(x)x = self.fc4(x)x = tf.nn.relu(x)x = self.fc5(x) return xnetwork = MyModel()network.compile(optimizer=optimizers.Adam(lr=0.01),loss=tf.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])network.fit(db, epochs=5, validation_data=ds_val,validation_freq=2)network.evaluate(ds_val)sample = next(iter(ds_val))
x = sample[0]
y = sample[1] # one-hot
pred = network.predict(x) # [b, 10]
# convert back to number 
y = tf.argmax(y, axis=1)
pred = tf.argmax(pred, axis=1)print(pred)
print(y)