Detectron 保存faster rcnn 测试结果，类别 置信度 坐标

 

由于项目需要，要求获取每张图片中每个box的类别、置信度得分和bbox的坐标信息。

思路在inference阶段，每infer一张图片就新开一个txt文件，txt文件的每一行代表一个bbox得检测信息包括bbox的类别 置信度 和四个坐标值

 

需要修改两个文件

1，修改  detectron-master/detectron/utils/vis.py 文件

2，修改  detectron-master/tools/infer_simple.py 文件

 

对于detectron-master/detectron/utils/vis.py 文件主要修改vis_one_image()函数,添加了一个参数用于传入txt的文件名字。

另外新添加一个函数get_class_and_confidence用于获取类别和置信度，该函数放在get_class_string杉树下面 如下图：

函数get_class_and_confidence在函数vis_one_image中调用获取类别和置信度得分，修改后的vis_one_image函数如下

def vis_one_image(
        im, im_name, output_dir, boxes, segms=None, keypoints=None, thresh=0.9,
        kp_thresh=2, dpi=200, box_alpha=0.0, dataset=None, show_class=False,
        ext='pdf', out_when_no_box=False,tested_txt=None):
    """Visual debugging of detections."""
    assert not (tested_txt==None),"please give the output full txt name"
    print("save detect reselt in : %s",tested_txt)
    save_to_txt = open(tested_txt,'w',encoding='utf-8')
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    if isinstance(boxes, list):
        boxes, segms, keypoints, classes = convert_from_cls_format(
            boxes, segms, keypoints)

    if (boxes is None or boxes.shape[0] == 0 or max(boxes[:, 4]) < thresh) and not out_when_no_box:
        return

    dataset_keypoints, _ = keypoint_utils.get_keypoints()

    if segms is not None and len(segms) > 0:
        masks = mask_util.decode(segms)

    color_list = colormap(rgb=True) / 255

    kp_lines = kp_connections(dataset_keypoints)
    cmap = plt.get_cmap('rainbow')
    colors = [cmap(i) for i in np.linspace(0, 1, len(kp_lines) + 2)]

    fig = plt.figure(frameon=False)
    fig.set_size_inches(im.shape[1] / dpi, im.shape[0] / dpi)
    ax = plt.Axes(fig, [0., 0., 1., 1.])
    ax.axis('off')
    fig.add_axes(ax)
    ax.imshow(im)

    if boxes is None:
        sorted_inds = [] # avoid crash when 'boxes' is None
    else:
        # Display in largest to smallest order to reduce occlusion
        areas = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
        sorted_inds = np.argsort(-areas)

    mask_color_id = 0
    for i in sorted_inds:
        bbox = boxes[i, :4]
        score = boxes[i, -1]
        if score < thresh:
            continue

        # show box (off by default)
        ax.add_patch(
            plt.Rectangle((bbox[0], bbox[1]),
                          bbox[2] - bbox[0],
                          bbox[3] - bbox[1],
                          fill=False, edgecolor='g',
                          linewidth=0.5, alpha=box_alpha))
        # print(classes[i],score,bbox)
        mycls,confidence = get_class_and_confidence(classes[i], score, dataset)
        write_linedata = "class:"+mycls+" "+"score:"+confidence+" "+"xmin:"+bbox[0]+" "+"ymin:"+bbox[1]+" "+"xmax:"+bbox[2]+" "+"ymax:"+bbox[3]
        save_to_txt.write(write_linedata + '\n')
        if show_class:
            ax.text(
                bbox[0], bbox[1] - 2,
                get_class_string(classes[i], score, dataset),
                fontsize=3,
                family='serif',
                bbox=dict(
                    facecolor='g', alpha=0.4, pad=0, edgecolor='none'),
                color='white')

        # show mask
        if segms is not None and len(segms) > i:
            img = np.ones(im.shape)
            color_mask = color_list[mask_color_id % len(color_list), 0:3]
            mask_color_id += 1

            w_ratio = .4
            for c in range(3):
                color_mask[c] = color_mask[c] * (1 - w_ratio) + w_ratio
            for c in range(3):
                img[:, :, c] = color_mask[c]
            e = masks[:, :, i]

            _, contour, hier = cv2.findContours(
                e.copy(), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)

            for c in contour:
                polygon = Polygon(
                    c.reshape((-1, 2)),
                    fill=True, facecolor=color_mask,
                    edgecolor='w', linewidth=1.2,
                    alpha=0.5)
                ax.add_patch(polygon)

        # show keypoints
        if keypoints is not None and len(keypoints) > i:
            kps = keypoints[i]
            plt.autoscale(False)
            for l in range(len(kp_lines)):
                i1 = kp_lines[l][0]
                i2 = kp_lines[l][1]
                if kps[2, i1] > kp_thresh and kps[2, i2] > kp_thresh:
                    x = [kps[0, i1], kps[0, i2]]
                    y = [kps[1, i1], kps[1, i2]]
                    line = plt.plot(x, y)
                    plt.setp(line, color=colors[l], linewidth=1.0, alpha=0.7)
                if kps[2, i1] > kp_thresh:
                    plt.plot(
                        kps[0, i1], kps[1, i1], '.', color=colors[l],
                        markersize=3.0, alpha=0.7)

                if kps[2, i2] > kp_thresh:
                    plt.plot(
                        kps[0, i2], kps[1, i2], '.', color=colors[l],
                        markersize=3.0, alpha=0.7)

            # add mid shoulder / mid hip for better visualization
            mid_shoulder = (
                kps[:2, dataset_keypoints.index('right_shoulder')] +
                kps[:2, dataset_keypoints.index('left_shoulder')]) / 2.0
            sc_mid_shoulder = np.minimum(
                kps[2, dataset_keypoints.index('right_shoulder')],
                kps[2, dataset_keypoints.index('left_shoulder')])
            mid_hip = (
                kps[:2, dataset_keypoints.index('right_hip')] +
                kps[:2, dataset_keypoints.index('left_hip')]) / 2.0
            sc_mid_hip = np.minimum(
                kps[2, dataset_keypoints.index('right_hip')],
                kps[2, dataset_keypoints.index('left_hip')])
            if (sc_mid_shoulder > kp_thresh and
                    kps[2, dataset_keypoints.index('nose')] > kp_thresh):
                x = [mid_shoulder[0], kps[0, dataset_keypoints.index('nose')]]
                y = [mid_shoulder[1], kps[1, dataset_keypoints.index('nose')]]
                line = plt.plot(x, y)
                plt.setp(
                    line, color=colors[len(kp_lines)], linewidth=1.0, alpha=0.7)
            if sc_mid_shoulder > kp_thresh and sc_mid_hip > kp_thresh:
                x = [mid_shoulder[0], mid_hip[0]]
                y = [mid_shoulder[1], mid_hip[1]]
                line = plt.plot(x, y)
                plt.setp(
                    line, color=colors[len(kp_lines) + 1], linewidth=1.0,
                    alpha=0.7)
    save_to_txt.close()

 

 

对于detectron-master/tools/infer_simple.py 文件，主要修改main函数，创建了一个文件夹（默认在detectron-master目录一下）output_txts用来存放每一张图片的txt。

修改后的main()函数

def main(args):
    logger = logging.getLogger(__name__)

    merge_cfg_from_file(args.cfg)
    cfg.NUM_GPUS = 1
    args.weights = cache_url(args.weights, cfg.DOWNLOAD_CACHE)
    assert_and_infer_cfg(cache_urls=False)

    assert not cfg.MODEL.RPN_ONLY, \
        'RPN models are not supported'
    assert not cfg.TEST.PRECOMPUTED_PROPOSALS, \
        'Models that require precomputed proposals are not supported'

    model = infer_engine.initialize_model_from_cfg(args.weights)
    dummy_coco_dataset = dummy_datasets.get_coco_dataset()

    if os.path.isdir(args.im_or_folder):
        im_list = glob.iglob(args.im_or_folder + '/*.' + args.image_ext)
    else:
        im_list = [args.im_or_folder]

    script_path = os.path.dirname(os.path.abspath(__file__))
    txt_path = "{0}/../output_txts/".format(script_path)
    if not os.path.exists():
        os.makedirs(txt_path)
    else:
        print("path exists,it should be removed!!")
    for i, im_name in enumerate(im_list):
        out_name = os.path.join(
            args.output_dir, '{}'.format(os.path.basename(im_name) + '.' + args.output_ext)
        )
        logger.info('Processing {} -> {}'.format(im_name, out_name))
        im = cv2.imread(im_name)
        timers = defaultdict(Timer)
        t = time.time()
        with c2_utils.NamedCudaScope(0):
            cls_boxes, cls_segms, cls_keyps = infer_engine.im_detect_all(
                model, im, None, timers=timers
            )
        print
        logger.info('Inference time: {:.3f}s'.format(time.time() - t))
        for k, v in timers.items():
            logger.info(' | {}: {:.3f}s'.format(k, v.average_time))
        if i == 0:
            logger.info(
                ' \ Note: inference on the first image will be slower than the '
                'rest (caches and auto-tuning need to warm up)'
            )
        #add save txt path
        txt_name = im_name.split(".")[0] + '.txt'
        save_txt_path = txt_path + txt_name
        vis_utils.vis_one_image(
            im[:, :, ::-1],  # BGR -> RGB for visualization
            im_name,
            args.output_dir,
            cls_boxes,
            cls_segms,
            cls_keyps,
            dataset=dummy_coco_dataset,
            box_alpha=0.3,
            show_class=True,
            thresh=args.thresh,
            kp_thresh=args.kp_thresh,
            ext=args.output_ext,
            out_when_no_box=args.out_when_no_box,
            tested_txt=save_txt_path
        )