transformer_19.py

H = 2
NUM_LAYERS = 2

en_vocab_size = len(en_tokenizer.word_index) + 1
encoder = Encoder(en_vocab_size, MODEL_SIZE, NUM_LAYERS, H)

en_sequence_in = tf.constant([[1, 2, 3, 4, 6, 7, 8, 0, 0, 0], 
                           [1, 2, 3, 4, 6, 7, 8, 0, 0, 0]])
encoder_output = encoder(en_sequence_in)

print('Input vocabulary size', en_vocab_size)
print('Encoder input shape', en_sequence_in.shape)
print('Encoder output shape', encoder_output.shape)

fr_vocab_size = len(fr_tokenizer.word_index) + 1
max_len_fr = data_fr_in.shape[1]
decoder = Decoder(fr_vocab_size, MODEL_SIZE, NUM_LAYERS, H)

fr_sequence_in = tf.constant([[1, 2, 3, 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0],
                           [1, 2, 3, 4, 5, 6, 7, 0, 0, 0, 0, 0, 0, 0]])
decoder_output = decoder(fr_sequence_in, encoder_output)

print('Target vocabulary size', fr_vocab_size)
print('Decoder input shape', fr_sequence_in.shape)
print('Decoder output shape', decoder_output.shape)