Function eval_epoch

classification/main_deepspeed.py:282–333

(config, data_loader, model, epoch=None)

@torch.no_grad()
def eval_epoch(config, data_loader, model, epoch=None):
    criterion = torch.nn.CrossEntropyLoss()
    model.eval()

    batch_time = AverageMeter()
    loss_meter = AverageMeter()
    acc1_meter = AverageMeter()
    acc5_meter = AverageMeter()

    end = time.time()
    for idx, (images, target) in enumerate(data_loader):
        images = images.cuda(non_blocking=True)
        target = target.cuda(non_blocking=True)
        output = model(images)

        # convert 22k to 1k to evaluate
        if output.size(-1) == 21841:
            convert_file = './meta_data/map22kto1k.txt'
            with open(convert_file, 'r') as f:
                convert_list = [int(line) for line in f.readlines()]
            output = output[:, convert_list]

        # measure accuracy and record loss
        loss = criterion(output, target)
        acc1, acc5 = accuracy(output, target, topk=(1, 5))

        acc1 = reduce_tensor(acc1)
        acc5 = reduce_tensor(acc5)
        loss = reduce_tensor(loss)

        loss_meter.update(loss.item(), target.size(0))
        acc1_meter.update(acc1.item(), target.size(0))
        acc5_meter.update(acc5.item(), target.size(0))

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

        if idx % config.PRINT_FREQ == 0:
            memory_used = torch.cuda.max_memory_allocated() / (1024.0 * 1024.0)
            logger.info(f'Test: [{idx}/{len(data_loader)}]\t'
                        f'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                        f'Loss {loss_meter.val:.4f} ({loss_meter.avg:.4f})\t'
                        f'Acc@1 {acc1_meter.val:.3f} ({acc1_meter.avg:.3f})\t'
                        f'Acc@5 {acc5_meter.val:.3f} ({acc5_meter.avg:.3f})\t'
                        f'Mem {memory_used:.0f}MB')
    if epoch is not None:
        logger.info(f'[Epoch:{epoch}] * Acc@1 {acc1_meter.avg:.3f} Acc@5 {acc5_meter.avg:.3f}')
    else:
        logger.info(f' * Acc@1 {acc1_meter.avg:.3f} Acc@5 {acc5_meter.avg:.3f}')

    return acc1_meter.avg, acc5_meter.avg, loss_meter.avg


def train(config, ds_config):