原书出处
Natural Language Processing in Action, Second Edition
>>> def train(model, iterator, optimizer, criterion, clip): ... ... model.train() #1 ... epoch_loss = 0 ... ... for i, batch in enumerate(iterator): ... src = batch.src ... trg = batch.trg ... optimizer.zero_grad() ... output = model(src, trg[:,:-1]) #2 ... output_dim = output.shape[-1] ... output = output.contiguous().view(-1, output_dim) ... trg = trg[:,1:].contiguous().view(-1) ... loss = criterion(output, trg) ... loss.backward() ... torch.nn.utils.clip_grad_norm_(model.parameters(), clip)
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-9.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36