Python &引用；ValueError：步幅长度应为1、1或3，但为2“；使用ConvLSTM2D时

我有一个预先训练的模型，它的输出是形状（20,7,7256）

我使用

tf.keras.layers.reformate（（20,7,7256））

将此输出整形为

（无，20,7,7256）

，然后将其馈送到

convlsm2d

层

x = ConvLSTM2D(filters = 256,kernel_size = 3,strides=(1,1),padding='same',
               data_format = 'channels_last',return_state = True,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)

但每次运行上述代码时都会出现此错误

~\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\nn_ops.py in convolution_internal(input, filters, strides, padding, data_format, dilations, name, call_from_convolution)
    957     channel_index = 1 if data_format.startswith("NC") else n + 1
    958 
--> 959   strides = _get_sequence(strides, n, channel_index, "strides")
    960   dilations = _get_sequence(dilations, n, channel_index, "dilations")
    961 

~\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\ops\nn_ops.py in _get_sequence(value, n, channel_index, name)
     73     value = list(value)
     74   else:
---> 75     raise ValueError("{} should be of length 1, {} or {} but was {}".format(
     76         name, n, n + 2, current_n))
     77 

ValueError: strides should be of length 1, 1 or 3 but was 2

即使我给出了

步幅=（1,1）

，我也不明白是什么导致了问题？？这个问题的解决方案是什么

编辑

错误不在这个ConvLSTM2D层中，而是在我在此层之后添加的下一个ConvLSTM2D层中。我在这个层中使用了

return\u state=True

，但我的意图是使用

return\u sequences=True

，这导致了下一个ConvLSTM2D层中的错误

将

return\u状态

更改为

return\u序列

x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = True,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)
x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = False,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)

x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = True,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)
x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = False,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)

---

分辨率由用户指定。为了社区的利益，在回答部分提及决议-

错误不在这个

ConvLSTM2D

层中，而是在下一层中

ConvLSTM2D

我在这一层之后添加的层。我在这个层中使用了

return\u state=True

，但我的意图是使用

return\u sequences=True

这导致了下一层的错误

将

return\u state

更改为后，原始代码为

返回\u序列

x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = True,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)
x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = False,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)

x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = True,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)
x = ConvLSTM2D(filters = 256,kernel_size = 3,
               strides=(1,1),padding='same',return_sequences = False,
               kernel_initializer=tf.keras.initializers.he_normal(seed=16))(x)