1

我正在开发一个输入形状为(128,128,3). 我想在 CNN 层之后添加 LSTM 层Conv2D。但是，既然 LSTM 接受维度为 3 的输入，我如何重塑来自 Conv2D 的 4-dim 输出以馈入 LSTM？

我尝试以这种方式建模，但它给出了尺寸误差。

model = Sequential()
model.add(Conv2D(16, kernel_size=(3,3), activation='relu',input_shape=(128,128,3)))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(16, kernel_size=(3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(LSTM(16, return_sequences=False,input_shape=(30,30,16)))
model.add(Flatten())
model.add(LSTM(16, return_sequences=True))
model.add(Dense(units=2, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer=optimizers.Adam(lr=1e-5, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False), metrics=['accuracy'])
#model.build(input_shape=(128,128,3))
model.summary()

这是错误

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-190-aea1537745bd> in <module>()
     23 model.add(MaxPooling2D(pool_size=(2,2)))
     24 #model.add(GlobalAveragePooling2D())
---> 25 model.add(LSTM(16, return_sequences=False,input_shape=(30,30,16)))
     26 model.add(Flatten())
     27 #model.add(LSTM(16, return_sequences=True))

8 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    221                          'expected ndim=' + str(spec.ndim) + ', found ndim=' +
    222                          str(ndim) + '. Full shape received: ' +
--> 223                          str(tuple(shape)))
    224     if spec.max_ndim is not None:
    225       ndim = x.shape.rank

ValueError: Input 0 of layer lstm_37 is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: (None, 30, 30, 16)
4

0 回答 0