10/8周报 学习siamgat中testTracker测试过程代码模块

 理解的是作者的源码，地址 GitHub - ohhhyeahhh/SiamGAT: Code for the paper "Graph Attention Tracking". (CVPR2021)

project部分结构 

 一、从testTracker中的main()函数进入

def main():
    # load config
    cfg.merge_from_file(args.config)

    # Test dataset
    dataset_root='/1904server/share/Data/GOT_10k/full_data/test_data/test/'

    # set hyper parameters
    params = getattr(cfg.HP_SEARCH, args.dataset)
    cfg.TRACK.LR = params[0]
    cfg.TRACK.PENALTY_K = params[1]
    cfg.TRACK.WINDOW_INFLUENCE = params[2]

    model = ModelBuilder()

在ModelBuilder()https://blog.youkuaiyun.com/every_step/article/details/120684274中主要 

# build backbone
# build car head  分类和回归子网的包围盒预测
# build response map 

 # load model
    model = load_pretrain(model, args.snapshot).cuda().eval()
    # build tracker
    tracker = SiamGATTracker(model)

 在SiamGATTracker()https://blog.youkuaiyun.com/every_step/article/details/120686343里，主要包含两个函数 init()和tracker()

• initi：当idx == 0，即传入第一帧图片时，初始化参数，计算一些之后搜索区域的中心等
• tracker：idx不等于0，传入后续的帧，根据网络返回目标的box坐标。

    # create dataset
    dataset = DatasetFactory.create_dataset(name=args.dataset,
                                            dataset_root=dataset_root,
                                            load_img=False)

    model_name = args.snapshot.split('/')[-1].split('.')[-2]

    # OPE tracking
    for v_idx, video in enumerate(dataset):
        if args.video != '':
            # test one special video
            if video.name != args.video:
                continue
        toc = 0
        pred_bboxes = []
        track_times = []
        for idx, (img, gt_bbox) in enumerate(video):
            tic = cv2.getTickCount()

            if idx == 0:
                cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
                gt_bbox_ = [cx-(w-1)/2, cy-(h-1)/2, w, h]
                tracker.init(img, gt_bbox_)
                pred_bbox = gt_bbox_
                pred_bboxes.append(pred_bbox)
            else:
                outputs = tracker.track(img)
                pred_bbox = outputs['bbox']
                pred_bboxes.append(pred_bbox)
            toc += cv2.getTickCount() - tic
            track_times.append((cv2.getTickCount() - tic)/cv2.getTickFrequency())
            if idx == 0:
                cv2.destroyAllWindows()
            if args.vis and idx > 0:
                if not any(map(math.isnan,gt_bbox)):
                    gt_bbox = list(map(int, gt_bbox))
                    pred_bbox = list(map(int, pred_bbox))
                    cv2.rectangle(img, (gt_bbox[0], gt_bbox[1]),
                                  (gt_bbox[0]+gt_bbox[2], gt_bbox[1]+gt_bbox[3]), (0, 255, 0), 3)
                    cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]),
                                  (pred_bbox[0]+pred_bbox[2], pred_bbox[1]+pred_bbox[3]), (0, 255, 255), 3)
                    cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
                    cv2.imshow(video.name, img)
                    cv2.waitKey(1)
        toc /= cv2.getTickFrequency()

 跟踪并且框出目标。