RuntimeError: element 0 of tensors does not require grad and does not have a grad_

原创

流年若逝 2022-07-18 21:26:08 博主文章分类：深度学习 ©著作权

文章标签 batch tensorflow 深度学习 scala 解决方案 文章分类 云平台云计算

©著作权归作者所有：来自51CTO博客作者流年若逝的原创作品，请联系作者获取转载授权，否则将追究法律责任

文章目录

1. 问题描述
2. 解决方案

2.1 方案1
2.2 方案2

3. 参考文献

1. 问题描述

今天在跑代码的过程中，因为要训练一个模型然后在测试阶段使用PGD来生成相应的adv_image来测试这个模型，结果运行到测试阶段出现下面的问题。

报错如下：
RuntimeError: element 0 of tensors does not require grad and does not have a grad_

我的代码如下：

def validate_roubst(val_loader, model, criterion, epoch, args, log=None, tf_writer=None, flag='roubst_val'):
    batch_time = AverageMeter('Time', ':6.3f')
    losses = AverageMeter('Loss', ':.4e')
    top1 = AverageMeter('Acc@1', ':6.2f')
    top5 = AverageMeter('Acc@5', ':6.2f')

    
    # switch to evaluate mode
    model.eval（)
    all_preds = []
    all_targets = []
    
    
    with torch.no_grad():
        end = time.time()
        for i, (input, target) in enumerate(val_loader):
            if args.gpu is not None:
                # input = input.cuda(args.gpu, non_blocking=True)
                print('............')

            input = input.cuda(args.gpu, non_blocking=True)
            target = target.cuda(args.gpu, non_blocking=True)
            
            attack_method = PGD(model, args.device)
            adv_example = attack_method.generate(input, target, epsilon = 8/255, num_steps = 20, step_size = 0.01, clip_max = 1.0, clip_min = 0.0, print_process = False, bound = 'linf')

            # compute output
            output = model(adv_example)  # input
            loss = criterion(output, target)

            # measure accuracy and record loss
            acc1, acc5 = accuracy(output, target, topk=(1, 5))
            losses.update(loss.item(), input.size(0))
            top1.update(acc1[0], input.size(0))
            top5.update(acc5[0], input.size(0))

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

            _, pred = torch.max(output, 1)
            all_preds.extend(pred.cpu().numpy())
            all_targets.extend(target.cpu().numpy())

            if i % args.print_freq == 0:
                output = ('Test: [{0}/{1}]\t'
                            'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                            'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                            'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                            'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                    i, len(val_loader), batch_time=batch_time, loss=losses,
                    top1=top1, top5=top5))
                print(output)
        cf = confusion_matrix(all_targets, all_preds).astype(float)
        cls_cnt = cf.sum(axis=1)
        cls_hit = np.diag(cf)
        cls_acc = cls_hit / cls_cnt
        output = ('{flag} Results: Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f} Loss {loss.avg:.5f}'
                .format(flag=flag, top1=top1, top5=top5, loss=losses))
        out_cls_acc = '%s Class Accuracy: %s'%(flag,(np.array2string(cls_acc, separator=',', formatter={'float_kind':lambda x: "%.3f" % x})))
        print(output)
        print(out_cls_acc)
        if log is not None:
            log.write(output + '\n')
            log.write(out_cls_acc + '\n')
            log.flush()

        tf_writer.add_scalar('loss/test_'+ flag, losses.avg, epoch)
        tf_writer.add_scalar('acc/test_' + flag + '_top1', top1.avg, epoch)
        tf_writer.add_scalar('acc/test_' + flag + '_top5', top5.avg, epoch)
        tf_writer.add_scalars('acc/test_' + flag + '_cls_acc', {str(i):x for i, x in enumerate(cls_acc)}, epoch)

     return