Method validate

pycontrast/learning/linear_trainer.py:193–242

(self, epoch, val_loader, model, classifier, criterion)

        return top1.avg, top5.avg, losses.avg

    def validate(self, epoch, val_loader, model, classifier, criterion):
        time1 = time.time()
        args = self.args

        model.eval()
        classifier.eval()

        batch_time = AverageMeter()
        losses = AverageMeter()
        top1 = AverageMeter()
        top5 = AverageMeter()

        with torch.no_grad():
            end = time.time()
            for idx, (input, target) in enumerate(val_loader):
                input = input.float()
                input = input.cuda(args.gpu, non_blocking=True)
                target = target.cuda(args.gpu, non_blocking=True)

                # compute output
                feat = model(x=input, mode=2)
                output = classifier(feat)
                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()

                if args.local_rank == 0 and idx % args.print_freq == 0:
                    print('Test: [{0}/{1}]\t'
                          'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                          'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                          'Acc@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                          'Acc@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                           idx, len(val_loader), batch_time=batch_time,
                           loss=losses, top1=top1, top5=top5))

            print(' * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'
                  .format(top1=top1, top5=top5))

        time2 = time.time()
        print('eval epoch {}, total time {:.2f}'.format(epoch, time2 - time1))

        return top1.avg, top5.avg, losses.avg