strides should be of length 1, 1 or 3 but was 2
TimeDistributed中要先将x的维度reshape成想要的形状 x = Reshape((10,30,30,1))(x) x = TimeDistributed(Conv2D(filters=64,strides=(1,1), kernel_size=(3, 3), padding='valid', data_format='channels_last',),input_shape=(10, 30, 30, 1))(x)...