Question

可以看出，我在'error_giving_notebook'中使用了tf.function装饰器，它抛出ValueError，而同一笔记本没有任何更改，只是删除了tf.function装饰器在'non_problematic_notebook'中运行流畅。可能是什么原因？

Answer 1

这里的问题在于conv2d类的调用方法的返回值：

if self.bias:
  if self.pad == 'REFLECT':
    self.p = (self.filter_size - 1) // 2
    self.x = tf.pad(inputs, [[0, 0], [self.p, self.p], [self.p, self.p], [0, 0]], 'REFLECT')
    return Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride),
                                  padding='VALID', use_bias=True, kernel_initializer=self.w, bias_initializer=self.b)(self.x)
  else:
    return Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride),
                                  padding=self.pad, use_bias=True, kernel_initializer=self.w, bias_initializer=self.b)(inputs)
else:
   if self.pad == 'REFLECT':
      self.p = (self.filter_size - 1) // 2
      self.x = tf.pad(inputs, [[0, 0], [self.p, self.p], [self.p, self.p], [0, 0]], 'REFLECT')
      return Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride),
                                  padding='VALID', use_bias=False, kernel_initializer=self.w)(self.x)
   else:
      return Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride),
                                  padding=self.pad, use_bias=False, kernel_initializer=self.w)(inputs)

通过返回一个Conv2D对象tf。每次调用时都会创建变量（权重，conv层的偏差）

predictions = model(images)

用tf装饰的功能中的

。因此，例外。

解决此问题的一种可能方法是更改conv2d类中的build和call方法，如下所示：

def build(self, inputs):
  self.w = tf.random_normal_initializer(mean=0.0, stddev=1e-4)
  if self.bias:
    self.b = tf.constant_initializer(0.0)
  else:
    self.b = None

  self.conv_a = Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride), padding='VALID', use_bias=True, kernel_initializer=self.w, bias_initializer=self.b)
  self.conv_b = Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride), padding=self.pad, use_bias=True, kernel_initializer=self.w, bias_initializer=self.b)
  self.conv_c = Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride), padding='VALID', use_bias=False, kernel_initializer=self.w)
  self.conv_d = Conv2D(filters=self.filter_num, kernel_size=(self.filter_size, self.filter_size), strides=(self.stride, self.stride),padding=self.pad, use_bias=False, kernel_initializer=self.w)  

def call(self, inputs):
  if self.bias:
    if self.pad == 'REFLECT':
      self.p = (self.filter_size - 1) // 2
      self.x = tf.pad(inputs, [[0, 0], [self.p, self.p], [self.p, self.p], [0, 0]], 'REFLECT')
      return self.conv_a(self.x)
    else:
      return self.conv_b(inputs)
  else:
     if self.pad == 'REFLECT':
        self.p = (self.filter_size - 1) // 2
        self.x = tf.pad(inputs, [[0, 0], [self.p, self.p], [self.p, self.p], [0, 0]], 'REFLECT')
        return self.conv_c(self.x)
     else:
        return self.conv_d(inputs)

为了更好地了解AutoGraph以及@ tf.function的工作原理，我建议看看this

Answer 2

当您尝试在TF 2.0中使用函数装饰器时，请在导入TensorFlow之后通过使用以下行急于启用运行功能：

tf.config.experimental_run_functions_eagerly(True)

如果您想了解更多信息，请参考this链接。

运行Tensorflow 2.0代码会给出'ValueError：tf.function-decorated函数试图在非首次调用时创建变量的信息'。我究竟做错了什么？

2 个答案: