Deep Learning Quick Reference

Without GloVe vectors

Let's demonstrate the code for an embedding layer without pretrained word vectors first. This code should look almost the same as the code in the previous example:

sequence_input = Input(shape=(sequence_length,), dtype='int32')embedding_layer = Embedding(input_dim=vocab_size,                            output_dim=embedding_dim,                            input_length=sequence_length,                            name="embedding")(sequence_input)