Crossentropy to NLL Loss

keon / seq2seq

Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch

MIT License

689 stars 172 forks source link

Closed pskrunner14 closed 6 years ago

pskrunner14 commented 6 years ago

Changed crossentropy to nll_loss as crossentropy criterion combines log_softmax and nll_loss in a single function. Fixes #4

keon commented 6 years ago

thanks so much :)