인프런 커뮤니티 질문&답변

안녕하세요 강사님 mmdetection 관련해서 이론적으로나 실무적으로나 항상 많은 도움 받고있습니다. 

강의 내용을 바탕으로 mmdetection code를 작성하던 도중 질문사항이 생겨서요 ㅎㅎ

 

mmdetection Mask R-CNN 모델을 이용하여 추론결과 아래 사진과 같이 

mask, bbox 두가지가 나타나는데 bbox위에 나타나는 title(coin) 대신 변수를 표시하고 싶습니다. 

class name, confidence score 가 아닌 ID, pixel number를 표시하고 싶습니다.

 

제 코드는 다음과 같습니다. 

img_name = path_dir + '/' + file_list[i]
        img_arr= cv2.imread(img_name, cv2.IMREAD_COLOR)
        img_arr_rgb = cv2.cvtColor(img_arr, cv2.COLOR_BGR2RGB)
        # cv2.imshow('img',img)
        fig= plt.figure(figsize=(12, 12))
        plt.imshow(img_arr_rgb)

        # inference_detector의 인자로 string(file경로), ndarray가 단일 또는 list형태로 입력 될 수 있음. 
        results = inference_detector(model, img_arr)

        #추론결과 디렉토리에 저장
        model.show_result(img_arr, results, score_thr=0.8, title=  bbox_color=(0,0,255),thickness=0.5,font_size=7, out_file= f'{save_dir1}{file_list[i]}')

 

이 결과 추론되는 사진은 다음과 같습니다 

 

아래는 mmdetection/mmdet/core/visualization/image.py에 있는 imshow_det_bboxes 함수입니다.

아래 함수가 시각화 해주는 함수여서 해당 함수를 수정하면 될 것 같은데 

아무리 뜯어봐도 어디를 고쳐야할 지 도저히 감이 오질 않습니다 ...ㅠㅠ

def imshow_det_bboxes(img,
                      bboxes,
                      labels,
                      segms=None,
                      class_names=None,
                      score_thr=0,
                      bbox_color='green',
                      text_color='green',
                      mask_color=None,
                      thickness=2,
                      font_size=13,
                      win_name='',
                      show=True,
                      wait_time=0,
                      out_file=None):
    """Draw bboxes and class labels (with scores) on an image.

    Args:
        img (str or ndarray): The image to be displayed.
        bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
            (n, 5).
        labels (ndarray): Labels of bboxes.
        segms (ndarray or None): Masks, shaped (n,h,w) or None
        class_names (list[str]): Names of each classes.
        score_thr (float): Minimum score of bboxes to be shown.  Default: 0
        bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
           The tuple of color should be in BGR order. Default: 'green'
        text_color (str or tuple(int) or :obj:`Color`):Color of texts.
           The tuple of color should be in BGR order. Default: 'green'
        mask_color (str or tuple(int) or :obj:`Color`, optional):
           Color of masks. The tuple of color should be in BGR order.
           Default: None
        thickness (int): Thickness of lines. Default: 2
        font_size (int): Font size of texts. Default: 13
        show (bool): Whether to show the image. Default: True
        win_name (str): The window name. Default: ''
        wait_time (float): Value of waitKey param. Default: 0.
        out_file (str, optional): The filename to write the image.
            Default: None

    Returns:
        ndarray: The image with bboxes drawn on it.
    """
    assert bboxes.ndim == 2, \
        f' bboxes ndim should be 2, but its ndim is {bboxes.ndim}.'
    assert labels.ndim == 1, \
        f' labels ndim should be 1, but its ndim is {labels.ndim}.'
    assert bboxes.shape[0] == labels.shape[0], \
        'bboxes.shape[0] and labels.shape[0] should have the same length.'
    assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5, \
        f' bboxes.shape[1] should be 4 or 5, but its {bboxes.shape[1]}.'
    img = mmcv.imread(img).astype(np.uint8)

    if score_thr > 0:
        assert bboxes.shape[1] == 5
        scores = bboxes[:, -1]
        inds = scores > score_thr
        bboxes = bboxes[inds, :]
        labels = labels[inds]
        if segms is not None:
            segms = segms[inds, ...]

    mask_colors = []
    if labels.shape[0] > 0:
        if mask_color is None:
            # Get random state before set seed, and restore random state later.
            # Prevent loss of randomness.
            # See: https://github.com/open-mmlab/mmdetection/issues/5844
            state = np.random.get_state()
            # random color
            np.random.seed(42)
            mask_colors = [
                np.random.randint(0, 256, (1, 3), dtype=np.uint8)
                for _ in range(max(labels) + 1)
            ]
            np.random.set_state(state)
        else:
            # specify  color
            mask_colors = [
                np.array(mmcv.color_val(mask_color)[::-1], dtype=np.uint8)
            ] * (
                max(labels) + 1)

    bbox_color = color_val_matplotlib(bbox_color)
    text_color = color_val_matplotlib(text_color)

    img = mmcv.bgr2rgb(img)
    width, height = img.shape[1], img.shape[0]
    img = np.ascontiguousarray(img)

    fig = plt.figure(win_name, frameon=False)
    plt.title(win_name)
    canvas = fig.canvas
    dpi = fig.get_dpi()
    # add a small EPS to avoid precision lost due to matplotlib's truncation
    # (https://github.com/matplotlib/matplotlib/issues/15363)
    fig.set_size_inches((width + EPS) / dpi, (height + EPS) / dpi)

    # remove white edges by set subplot margin
    plt.subplots_adjust(left=0, right=1, bottom=0, top=1)
    ax = plt.gca()
    ax.axis('off')

    polygons = []
    color = []
    for i, (bbox, label) in enumerate(zip(bboxes, labels)):
        bbox_int = bbox.astype(np.int32)
        poly = [[bbox_int[0], bbox_int[1]], [bbox_int[0], bbox_int[3]],
                [bbox_int[2], bbox_int[3]], [bbox_int[2], bbox_int[1]]]
        np_poly = np.array(poly).reshape((4, 2))
        polygons.append(Polygon(np_poly))
        color.append(bbox_color)
        label_text = class_names[
            label] if class_names is not None else f'class {label}'
        if len(bbox) > 4:
            label_text += f'|{bbox[-1]:.02f}'
        ax.text(
            bbox_int[0],
            bbox_int[1],
            f'{label_text}',
            bbox={
                'facecolor': 'black',
                'alpha': 0.8,
                'pad': 0.7,
                'edgecolor': 'none'
            },
            color=text_color,
            fontsize=font_size,
            verticalalignment='top',
            horizontalalignment='left')
        if segms is not None:
            color_mask = mask_colors[labels[i]]
            mask = segms[i].astype(bool)
            img[mask] = img[mask] * 0.5 + color_mask * 0.5

    plt.imshow(img)

    p = PatchCollection(
        polygons, facecolor='none', edgecolors=color, linewidths=thickness)
    ax.add_collection(p)

    stream, _ = canvas.print_to_buffer()
    buffer = np.frombuffer(stream, dtype='uint8')
    img_rgba = buffer.reshape(height, width, 4)
    rgb, alpha = np.split(img_rgba, [3], axis=2)
    img = rgb.astype('uint8')
    img = mmcv.rgb2bgr(img)

    if show:
        # We do not use cv2 for display because in some cases, opencv will
        # conflict with Qt, it will output a warning: Current thread
        # is not the object's thread. You can refer to
        # https://github.com/opencv/opencv-python/issues/46 for details
        if wait_time == 0:
            plt.show()
        else:
            plt.show(block=False)
            plt.pause(wait_time)
    if out_file is not None:
        mmcv.imwrite(img, out_file)

    plt.close()

    return img

 

감사합니다