I am trying to build a sequence to sequence encoder decoder network for language translation (English to French), I use three BLSTM layers with dropout as encoder and one LSTM decoder.
For the model and the fit is ok, but I keep getting an error in the inference model.
The error says:
ValueError: Layer lstm_3 expects 35 inputs, but it received 3 input tensors. Inputs received: [<tf.Tensor 'embedding_1/embedding_lookup_25/Identity_1:0' shape=(None, None, 128) dtype=float32>, <tf.Tensor 'input_87:0' shape=(None, 128) dtype=float32>, <tf.Tensor 'input_88:0' shape=(None, 128) dtype=float32>]
This is my Model:
latent_dim = 128
# Encoder
encoder_inputs = Input(shape=(max_length_english,))
enc_emb = Embedding(vocab_size_source, latent_dim,trainable=True)(encoder_inputs)
#LSTM 1
encoder_lstm1 = LSTM(latent_dim, recurrent_dropout= 0.6,return_sequences=True,return_state=True)
encoder_output1, state_h1, state_c1 = encoder_lstm1(enc_emb)
#LSTM 2
encoder_lstm2 = LSTM(latent_dim, recurrent_dropout= 0.6,return_sequences=True,return_state=True)
encoder_output2, state_h2, state_c2 = encoder_lstm2(encoder_output1)
#LSTM 3
encoder_lstm3=LSTM(latent_dim, recurrent_dropout= 0.6, return_state=True, return_sequences=True)
encoder_outputs, state_h, state_c= encoder_lstm3(encoder_output2)
# Set up the decoder.
decoder_inputs = Input(shape=(None,))
dec_emb_layer = Embedding(vocab_size_target, latent_dim,trainable=True)
dec_emb = dec_emb_layer(decoder_inputs)
#LSTM using encoder_states as initial state
decoder_lstm = LSTM(latent_dim, recurrent_dropout= 0.6, return_sequences=True, return_state=True)
decoder_outputs,decoder_fwd_state, decoder_back_state = decoder_lstm(dec_emb,initial_state=[state_h, state_c])
#Dense layer
decoder_dense = Dense(vocab_size_target, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
# Define the model
model1 = Model([encoder_inputs, decoder_inputs], decoder_outputs)
And this is my inference mode:
latent_dim=128
# encoder inference
encoder_inputs = model_loaded.input[0] #loading encoder_inputs
encoder_outputs, state_h, state_c = model_loaded.layers[6].output #loading encoder_outputs
print(encoder_outputs.shape)
encoder_model = Model(inputs=encoder_inputs,outputs=[encoder_outputs, state_h, state_c])
# decoder inference
# Below tensors will hold the states of the previous time step
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_hidden_state_input = Input(shape=(32,latent_dim))
# Get the embeddings of the decoder sequence
decoder_inputs = model_loaded.layers[3].output
print(decoder_inputs.shape)
dec_emb_layer = model_loaded.layers[5]
dec_emb2= dec_emb_layer(decoder_inputs)
# To predict the next word in the sequence, set the initial states to the states from the previous time step
decoder_lstm = model_loaded.layers[7]
decoder_outputs2, state_h2, state_c2 = decoder_lstm(dec_emb2, initial_state=[decoder_state_input_h, decoder_state_input_c])
# A dense softmax layer to generate prob dist. over the target vocabulary
decoder_dense = model_loaded.layers[8]
decoder_outputs = decoder_dense(decoder_outputs2)
# Final decoder model
decoder_model = Model(
[decoder_inputs] + [decoder_hidden_state_input,decoder_state_input_h, decoder_state_input_c],
[decoder_outputs2] + [state_h2, state_c2])
For optimzer rmsprop and loss
model1.compile(optimizer='rmsprop' and for loss 'sparse_categorical_crossentropy'
loss='sparse_categorical_crossentropy', #sparse_categorical_crossentropy
metrics=['accuracy'])
And finally for val_loss and val_accury after 57 epochs I have this result:
Epoch 57/100
55/55 [==============================] - 197s 4s/step - loss: 0.7188 - accuracy: 0.8474 - val_loss: 0.9559 - val_accuracy: 0.8271
Epoch 00057: early stopping