scheduler.step()
err.update(loss.item())
grd.update(grad_norm)
writer.add_scalar(err.title + '/steps', loss.item(), step)
writer.add_scalar(grd.title + '/steps', grad_norm, step)
loader.set_description('Epoch %d %s %s' % (epoch, err, grd))
model.eval()
for i, lr in enumerate(scheduler.get_lr()):
writer.add_scalar('LR/%d' % i, lr, epoch)
err.summary(writer, epoch)
grd.summary(writer, epoch)
err = AverageMeter('Loss/test')
loader = DataLoaderCuda(test, batch_size=bptt, drop_last=True)
hidden = model.step_init(batch_size)
with torch.no_grad():
for inputs, targets in loader:
output, hidden = model.step_forward(inputs, hidden)
loss = criterion(output, targets.view(-1))
grd.update(grad_norm)
writer.add_scalar(grd.title + '/steps', grad_norm, step)
train.set_description('Epoch %d %s %s %s %s' % (epoch, err, ent, grd, rwd))
if step % 200 == 0:
train.close()
break
model.eval()
for i, lr in enumerate(scheduler.get_lr()):
writer.add_scalar('LR/%d' % i, lr, epoch)
err.summary(writer, epoch)
ent.summary(writer, epoch)
grd.summary(writer, epoch)
rwd.summary(writer, epoch)
err = AverageMeter('Loss/test')
ent = AverageMeter('Entropy/test')
cer = AverageCER(blank, space)
wer = AverageWER(blank, space)
with torch.no_grad():
for xs, ys, xn, yn in test:
zs, xs, xn = model(xs, ys.t(), xn, yn)
