ValueError:层lstm_14的输入0与层不兼容:应为ndim=3，实际为ndim=4.收到完整形状:[无，12

Question

我正在使用CNN-LSTM网络进行图像分类。我的图像大小是(2242243)，批量大小是90。当我将输入传递到LSTM层时，我得到了这个错误。以下是我的代码片段：

input1 = Input(shape=(224, 224,3))
x = Conv2D(8, (3,3), activation ="relu")(input1)
x = MaxPooling2D(2,2)(x)
x = Conv2D(16, (3,3), activation ="relu")(x)
x = MaxPooling2D(2,2)(x)
x = Conv2D(32, (3,3), activation ="relu")(x)
x = MaxPooling2D(2,2)(x)
x = Conv2D(64, (3,3), activation ="relu")(x)
x = Dropout(0.2)(x)
x = MaxPooling2D(2,2)(x)
x = LSTM(units= 64, activation= 'tanh', input_shape= [None, 144], return_sequences = True)(x)
error:
---> 10 x = LSTM(units= 64, activation= 'tanh', input_shape= [None, 144], return_sequences = True)(x)
ValueError: Input 0 of layer lstm_14 is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: [None, 12, 12, 64]

如果有人能解决我的问题，谢谢。

Answer 1

根据文档页面，LSTM层输入应具有以下形状：[batch, timesteps, feature]。您的LSTM层接收形状[None, 12, 12, 64]的输入，这就是为什么您获得关于3D/4D形状的错误。你需要重塑你的张量：[None, 12, 12, 64] -> [None, 144, 64]。为此，可以在上一个MaxPooling2D和LSTM层之间插入Reshape层。