You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I changed / to // in the following line of code of beam_search.py, and the problem is solved,
beams_order = best_scores_id.squeeze(1)//n_extended_vocab
Hi, when I want to run either validation or testing phase, there is an error in the advance function of beamsearch as below:
self.hid_h = h[beams_order] #(beam, n_hid); sorted
IndexError: tensors used as indices must be long, byte or bool tensors
the output for beams_order is tensor([0.0557, 0.0172, 0.0002, 0.0270], device='cuda:0')
The text was updated successfully, but these errors were encountered: