Search code examples
kerasword2veckeras-layerkeras-2

how to use Merge in kerase>2.0?

word_model=Sequential() word_model.add(Embedding(vocab_size,embed_size,               embeddings_initializer="glorot_uniform",               input_length=1)) word_model.add(Reshape((embed_size,)))

context_model=Sequential() context_model.add(Embedding(vocab_size,embed_size,               embeddings_initializer="glorot_uniform",               input_length=1)) context_model.add(Reshape((embed_size,)))

model=Sequential()model.add(Merge([word_model,context_model],mode="dot")) model.add(Dense(1,init="glorot_unifor",activation="sigmod")) model.compile(loss="mean_squared_error",optimizer="adam")

how to change those in keras2, which has no merge methods any more

Solution

  • The Merge API has been changed. The new API is documented here.

    In your example, instead of doing this:
    Merge([word_model,context_model],mode="dot")

    Do this:
    keras.layers.dot([word_model,context_model])

    and it should work!