tensorflow之自定义神经网络层实例

import tensorflow as tf
tfe = tf.contrib.eager

tf.enable_eager_execution()

#在tf.keras.layers包中，图层是对象。要构造一个图层，只需构造一个对象。大多数层将输出维度/通道的数量作为第一个参数。
layer=tf.keras.layers.Dense(100)
#输入维度的数量通常是不必要的，因为它可以在第一次使用图层时推断出来，但如果您想手动指定它，则可以提供它，这在某些复杂模型中很有用。
layer=tf.keras.layers.Dense(10,input_shape=(None,5))
#调用层
layer(tf.zeros([10,5]))
 

#图层有许多有用的方法。例如，您可以通过调用layer.variables来检查图层中的所有变量。在这种情况下，完全连接的层将具有权重和偏差的变量。
variable=layer.variables
# variable[0]
layer.kernel.numpy()
layer.bias

class MyDenseLayer(tf.keras.layers.Layer):
 def __init__(self, num_outputs):
  super(MyDenseLayer, self).__init__()
  self.num_outputs = num_outputs
  
 def build(self, input_shape):
  self.kernel = self.add_variable("kernel", 
                  shape=[input_shape[-1].value, 
                      self.num_outputs])
  
 def call(self, input):
  return tf.matmul(input, self.kernel)
 
layer = MyDenseLayer(10)
print(layer(tf.zeros([10, 5])))
print(layer.variables)

class ResnetIdentityBlock(tf.keras.Model):
 def __init__(self, kernel_size, filters):
  super(ResnetIdentityBlock, self).__init__(name='')
  filters1, filters2, filters3 = filters
 
  self.conv2a = tf.keras.layers.Conv2D(filters1, (1, 1))
  self.bn2a = tf.keras.layers.BatchNormalization()
 
  self.conv2b = tf.keras.layers.Conv2D(filters2, kernel_size, padding='same')
  self.bn2b = tf.keras.layers.BatchNormalization()
 
  self.conv2c = tf.keras.layers.Conv2D(filters3, (1, 1))
  self.bn2c = tf.keras.layers.BatchNormalization()
 
 def call(self, input_tensor, training=False):
  x = self.conv2a(input_tensor)
  x = self.bn2a(x, training=training)
  x = tf.nn.relu(x)
 
  x = self.conv2b(x)
  x = self.bn2b(x, training=training)
  x = tf.nn.relu(x)
 
  x = self.conv2c(x)
  x = self.bn2c(x, training=training)
 
  x += input_tensor
  return tf.nn.relu(x)
 
  
block = ResnetIdentityBlock(1, [1, 2, 3])
print(block(tf.zeros([1, 2, 3, 3])))
print([x.name for x in block.variables])