I am using tf.sampled_softmax_loss in a RNN for translation from english to french. This is usefull to speed up the training but, is it possible to get the prediction of the samples used by tf.sampled_softmax_loss ?
I'd like to be able to compute the accuracy.
Indeed, what I understand is that tf.sampled_softmax_loss acte like a final layer that output all the logits for all the required class, and then apply the sampled algrithm to proccess a "smaller" softmax. But, I can't directly access, at least, the logits.
I am using
tf.sampled_softmax_lossin a RNN for translation from english to french. This is usefull to speed up the training but, is it possible to get the prediction of the samples used bytf.sampled_softmax_loss?I'd like to be able to compute the accuracy.
Indeed, what I understand is that
tf.sampled_softmax_lossacte like a final layer that output all the logits for all the required class, and then apply the sampled algrithm to proccess a "smaller" softmax. But, I can't directly access, at least, the logits.