keras - 保存和加载 keras 自动编码器

Question

看看这个奇怪的加载/保存模型情况。我保存了变分自动编码器模型及其编码器和解码器：

autoencoder.save("autoencoder_save", overwrite=True)
encoder.save("encoder_save", overwrite=True)
decoder.save("decoder_save", overwrite=T)

之后，我从磁盘加载了所有内容：

autoencoder_disk = load_model("autoencoder_save", custom_objects={'KLDivergenceLayer': KLDivergenceLayer,
                                                       'nll': nll})
encoder_disk = load_model("encoder_save", custom_objects={'KLDivergenceLayer': KLDivergenceLayer,
                                                       'nll': nll})
decoder_disk = load_model("decoder_save", custom_objects={'KLDivergenceLayer': KLDivergenceLayer,
                                                       'nll': nll})

如果我尝试

x_test_encoded = encoder_disk.predict(x_test,batch_size=batch_size)
x_test_decoded = decoder_disk.predict(x_test_encoded)
print(np.round(x_test_decoded[3]))

一切都很好，就像我使用内存中的编码器/解码器一样，但是如果我尝试

vae = autoencoder_disk.predict(x_test_encoded) 

我有

ValueError: Error when checking model : the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s) but instead got the following list of 1 arrays:...

尽管我可以从内存中的变分自动编码器中进行预测。为什么自动编码器从磁盘加载时不起作用？

标签： kerasautoencoder

Answer 1

您将编码的输出x_test_encoded作为输入传递给 autoencoder autoencoder_disk.predict(x_test_encoded)。您应该传递编码器期望的原始输入x_test。