如何从KERAS中的加载模型构造编码器

Question

我有一个编码器模型，其结构与 num_encoder_tokens = 1949的Machinelearningmastery.com上的结构相同， num_decoder_tokens = 1944和latent_dim = 2048。

我想通过加载已经训练的模型并尝试解码一些示例来构造编码器和解码器模型，但是我会收到错误"Graph disconnected: cannot obtain value for tensor Tensor("input_1_1:0", shape=(?,?, 1949), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []。

我代码的一部分是：

encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
encoder_states = [state_h, state_c]
decoder_inputs = Input(shape=(None, num_decoder_tokens))
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
                                     initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
          batch_size=batch_size,
          epochs=epochs,
          validation_split=0.2)
model.save('modelname.h5')
# ...from here different python file for inference...
encoder = LSTM(latent_dim, return_state=True)
model = load_model('modelname.h5')
encoder_model = Model(model.output, encoder(model.output)) # I get the error here

我想在这里做的是：

encoder_inputs = Input(shape=(None, 1949))
encoder = LSTM(2048, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
encoder_states = [state_h, state_c]
encoder_model = Model(encoder_inputs, encoder_states)

如果有人可以帮助我，我会非常感谢。

Answer 1

看一下Robert Sim对Stack Overflow中此帖子的回答：Restore Keras seq2seq模型

以及Github中的这篇文章：https：//github.com/keras-team/keras/pull/9119。

他还提供了一个示例：https：//github.com/simra/keras/blob/simra/simra/s2srestore/examples/LSTM_SEQ2SEQ_RESTORE.PY，您可以在其中看到如何加载模型。以下代码是从该示例中获取的。

# Restore the model and construct the encoder and decoder.
model = load_model('s2s.h5')
encoder_inputs = model.input[0]   # input_1
encoder_outputs, state_h_enc, state_c_enc = model.layers[2].output   # lstm_1
encoder_states = [state_h_enc, state_c_enc]
encoder_model = Model(encoder_inputs, encoder_states)
decoder_inputs = model.input[1]   # input_2
decoder_state_input_h = Input(shape=(latent_dim,), name='input_3')
decoder_state_input_c = Input(shape=(latent_dim,), name='input_4')
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_lstm = model.layers[3]
decoder_outputs, state_h_dec, state_c_dec = decoder_lstm(
    decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h_dec, state_c_dec]
decoder_dense = model.layers[4]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
    [decoder_inputs] + decoder_states_inputs,
    [decoder_outputs] + decoder_states)