imagenet.py 文件源码

def train(train_loader, model, criterion, optimizer, epoch, use_cuda):
    # switch to train mode
    model.train()

    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()
    end = time.time()

    bar = Bar('Processing', max=len(train_loader))
    for batch_idx, (inputs, targets) in enumerate(train_loader):
        # measure data loading time
        data_time.update(time.time() - end)

        if use_cuda:
            inputs, targets = inputs.cuda(), targets.cuda(async=True)
        inputs, targets = torch.autograd.Variable(inputs), torch.autograd.Variable(targets)

        # compute output
        outputs = model(inputs)
        loss = criterion(outputs, targets)

        # measure accuracy and record loss
        prec1, prec5 = accuracy(outputs.data, targets.data, topk=(1, 5))
        losses.update(loss.data[0], inputs.size(0))
        top1.update(prec1[0], inputs.size(0))
        top5.update(prec5[0], inputs.size(0))

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        # plot progress
        bar.suffix  = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | top1: {top1: .4f} | top5: {top5: .4f}'.format(
                    batch=batch_idx + 1,
                    size=len(train_loader),
                    data=data_time.val,
                    bt=batch_time.val,
                    total=bar.elapsed_td,
                    eta=bar.eta_td,
                    loss=losses.avg,
                    top1=top1.avg,
                    top5=top5.avg,
                    )
        bar.next()
    bar.finish()
    return (losses.avg, top1.avg)