Keras TimeDistributed Conv1D 错误

这是我的代码：

cnn_input = Input(shape=(cnn_max_length,)) 
emb_output = Embedding(num_chars + 1, output_dim=32, input_length=cnn_max_length, trainable=True)(cnn_input)
output = TimeDistributed(Convolution1D(filters=128, kernel_size=4, activation='relu'))(emb_output)

我想训练一个字符级 CNN 序列标记器，但我不断收到此错误：

Traceback (most recent call last):
  File "word_lstm_char_cnn.py", line 24, in <module>
    output = kl.TimeDistributed(kl.Convolution1D(filters=128, kernel_size=4, activation='relu'))(emb_output)
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/keras/engine/base_layer.py", line 457, in __call__
    output = self.call(inputs, **kwargs)
es/keras/layers/wrappers.py", line 248, in call
    y = self.layer.call(inputs, **kwargs)
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/keras/layers/convolutional.py", line 160, in call
    dilation_rate=self.dilation_rate[0])
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 3526, in conv1d
    data_format=tf_data_format)
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 779, in convolution
    data_format=data_format)
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 828, in __init__
    input_channels_dim = input_shape[num_spatial_dims + 1]
  File "/home/user/anaconda3/envs/thesisenv/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 615, in __getitem__
    return self._dims[key]
IndexError: list index out of range

输入应该是 3D 的。如果我更改输入形状，我会收到此错误：

ValueError: Input 0 is incompatible with layer time_distributed_1: expected ndim=3, found ndim=4

推荐解决方案: 没有必要使用TimeDistributed在这种情况下。您可以使用以下代码修复该问题：

output = Convolution1D(filters=128, kernel_size=4, activation='relu')(emb_output)

以防万一，如果你喜欢使用TimeDistributed你可以这样做：

output = TimeDistributed(Dense(100,activation='relu'))(emb_output)

不建议：根据文档：

该包装器将一个层应用于输入的每个时间切片。

输入到TimeDistributed是这样的batch_size * seq_len * emb_size. When Conv1D适用于每个序列，它需要 2 个维度，但只找到一个。

您可以通过向序列添加一维来解决该问题：

TimeDistributed(Conv1D(100, 1))(keras.backend.reshape(emb, [-1, sequence_len, embeding_dim, 1]))