Function do_inference

processor/processor.py:215–247

(cfg, model, val_loader, num_query)

def do_inference(cfg, model, val_loader, num_query):
    device = "cuda"
    logger = logging.getLogger("transreid.test")
    logger.info("Enter inferencing")

    evaluator = R1_mAP_eval(num_query, max_rank=50, feat_norm=cfg.TEST.FEAT_NORM)

    evaluator.reset()

    if device:
        if torch.cuda.device_count() > 1:
            print("Using {} GPUs for inference".format(torch.cuda.device_count()))
            model = nn.DataParallel(model)
        model.to(device)

    model.eval()
    img_path_list = []

    for n_iter, (img, pid, camid, camids, target_view, imgpath, img_wh) in enumerate(val_loader):
        with torch.no_grad():
            img = img.to(device)
            camids = camids.to(device)
            img_wh = img_wh.to(device)
            feat = model(img, cam_label=camids, img_wh=img_wh)
            evaluator.update((feat, pid, camid))
            img_path_list.extend(imgpath)

    cmc, mAP, _, _, _, _, _ = evaluator.compute()
    logger.info("Validation Results ")
    logger.info("mAP: {:.1%}".format(mAP))
    for r in [1, 5, 10]:
        logger.info("CMC curve, Rank-{:<3}:{:.1%}".format(r, cmc[r - 1]))
    return cmc[0], cmc[4]