keras add external trainable variable to graph

Question

I am working on language modelling and the vocabulary is large. So I want to use sampled_softmax_loss from tensorflow. The problem is that weights and

Answer 1

I have finally found a workaround

Let's say we need to train weights W and biases b with our model.

So the workaround is just add them to one of the trainable layers of our model.

model.layers[-1].trainable_weights.extend([W, b])

When we can compile the model

model.compile(...)

It is extremely important to add variables to trainable layer, for example I've experimented with Sequential model, and adding [W, b] to the Activation layer does not make them actually trainable.