Hi everyone,
I would like to know which is the best way to get the activations of a certain layer in the multifit model using backward hooks. If possible I would like to get grad_output from the embeddings layer in this model, is it possible?
Hi everyone,
I would like to know which is the best way to get the activations of a certain layer in the multifit model using backward hooks. If possible I would like to get grad_output from the embeddings layer in this model, is it possible?