Keras 自动编码器中的输入形状

Question

我正在尝试在以下代码中训练自动编码器：

encoder_input = keras.layers.Input(shape=(x_Train.shape[1]), name='img')
encoder_out = keras.layers.Dense(1, activation = "relu")(encoder_input)

encoder = keras.Model(encoder_input, encoder_out, name="encoder")

decoder_input = keras.layers.Dense(602896, activation = "relu")(encoder_out)
decoder_output = keras.layers.Reshape((769, 28, 28))(decoder_input)

opt = keras.optimizers.RMSprop(learning_rate=1e-3)

autoencoder = keras.Model(encoder_input, decoder_output, name = "autoencoder")
autoencoder.summary()

autoencoder.compile(opt, loss='mse')
autoencoder.fit(x_Train, x_Train, epochs=10, batch_size=64, validation_split = 0.1)

但是，它返回错误：“tensorflow:Model 是用形状 (None, 28) 构造的输入 KerasTensor(type_spec=TensorSpec(shape=(None, 28), dtype=tf.float32, name='img'), name ='img', description="created by layer 'img'")，但它是在形状不兼容的输入上调用的 (None, 28, 28)。”

我不知道如何处理或调整我的输入。 我的 x_train 是一个大小为 [769,28,28] 的向量

有人可以帮我处理错误吗？

这就是总结

谢谢

Answer 1

您的自动编码器的输入形状有点奇怪，您的训练数据的形状为 28x28，批次为 769，因此修复应该是这样的：

encoder_input = keras.layer.Input(shape=(28, 28), name='img')
encoder_out = keras.layers.Dense(1, activation = "relu")(encoder_input)

# For ur decoder, you need to change a bit as well
decoder_input = keras.layers.Dense(784, activation = "sigmoid")(encoder_out) # Flatten until 28x28 =784
decoder_output = keras.layers.Reshape((28, 28))(decoder_input) # From there reshape back to 28x28

Answer 2

我按照您的建议进行了更正，但它仍然返回以下错误：

ValueError                                Traceback (most recent call last)
<ipython-input-48-78f8cac6c724> in <module>()
      6 
      7 decoder_input = keras.layers.Dense(784, activation = "sigmoid")(encoder_out)
----> 8 decoder_output = keras.layers.Reshape((28, 28))(decoder_input)
      9 
     10 opt = keras.optimizers.RMSprop(learning_rate=1e-3)

6 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/core.py in _fix_unknown_dimension(self, input_shape, output_shape)
    534       output_shape[unknown] = original // known
    535     elif original != known:
--> 536       raise ValueError(msg)
    537     return output_shape
    538 

ValueError: total size of new array must be unchanged, input_shape = [28, 784], output_shape = [28, 28]

代码：

encoder_input = keras.layers.Input(shape=(28,28), name='img')
encoder_out = keras.layers.Dense(1, activation = "relu")(encoder_input)

encoder = keras.Model(encoder_input, encoder_out, name="encoder")

decoder_input = keras.layers.Dense(784, activation = "sigmoid")(encoder_out)
decoder_output = keras.layers.Reshape((28, 28))(decoder_input)

opt = keras.optimizers.RMSprop(learning_rate=1e-3)

autoencoder = keras.Model(encoder_input, decoder_output, name = "autoencoder")
autoencoder.summary()