无法构建在不规则张量上循环的 TensorFlow 自定义层答案

【问题标题】：Tesnorflow custom layer that loops over ragged tensor cannot be built无法构建在不规则张量上循环的 TensorFlow 自定义层
【发布时间】：2020-06-05 20:16:43
【问题描述】：

我正在尝试在 tensorflow 中自定义一个层。该层必须将具有未知长度的参差不齐的张量作为输入。但是在尝试构建层时代码被卡住了。即使是下面附加的简单代码也无法正常工作。

import tensorflow as tf
class myLayer(tf.keras.layers.Layer):
    def __init__(self):
        super(myLayer, self).__init__()
        self._supports_ragged_inputs = True


    def call(self, inputs):
        # Try to loop over ragged tensor
        for x in inputs:
            pass
        return tf.constant(0)

# Input is ragged tensor
inputs = tf.keras.layers.Input(shape=(None, 1), ragged=True)

layer1 = myLayer()
output = layer1(inputs)

【问题讨论】：

标签： python tensorflow recurrent-neural-network layer ragged

【解决方案1】：

当我在 Tensorflow version 2.2.0 中运行您的代码时，我在 for 循环中收到以下错误 -

错误 -

ValueError: in user code:

    <ipython-input-24-1681d59017fc>:10 call  *
        for x in inputs:
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:359 for_stmt
        iter_, extra_test, body, get_state, set_state, symbol_names, opts)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:491 _tf_ragged_for_stmt
        opts)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:885 _tf_while_stmt
        aug_test, aug_body, init_vars, **opts)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/control_flow_ops.py:2688 while_loop
        back_prop=back_prop)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/while_v2.py:104 while_loop
        maximum_iterations)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/while_v2.py:1258 _build_maximum_iterations_loop_var
        maximum_iterations, dtype=dtypes.int32, name="maximum_iterations")
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:1317 convert_to_tensor
        (dtype.name, value.dtype.name, value))

    ValueError: Tensor conversion requested dtype int32 for Tensor with dtype int64: <tf.Tensor 'my_layer_15/strided_slice:0' shape=() dtype=int64>

所以我只是做了下面的实验来了解for循环和enumerate在使用inputs时产生的数据类型。 for 循环生成一个tensor 类，而enumerate 生成一个int 类。

实验代码 -

inputs = tf.keras.layers.Input(shape=(None, 1), ragged=True)

for x in inputs:
  print(type(x))
  break

for i,x in enumerate(inputs):
  print(type(i))
  break

输出 -

<class 'tensorflow.python.framework.ops.Tensor'>
<class 'int'>

所以我修改了你的代码如下，它运行良好 -

固定代码 -

import tensorflow as tf
class myLayer(tf.keras.layers.Layer):
    def __init__(self):
        super(myLayer, self).__init__()
        self._supports_ragged_inputs = True


    def call(self, inputs):
        # Try to loop over ragged tensor
        # for x in inputs:  # Throws Error
        for i,x in enumerate(inputs): #Enumerate Works fine
          break                       #Using break as pass will go into loop 
        return tf.constant(0)

# Input is ragged tensor
inputs = tf.keras.layers.Input(shape=(None, 1), ragged=True)

layer1 = myLayer()
output = layer1(inputs)
print(output)

输出 -

Tensor("my_layer_17/Identity:0", shape=(), dtype=int32)

希望这能回答您的问题。快乐学习。

【讨论】：

@Jing - 希望我们已经回答了您的问题。如果您对答案感到满意，请您接受并投票。