Question

我已经成功训练了Mask_RCNN，并且出于说明目的，让我们关注网络生成的示例图像：

一切都很好，没问题。但是，我想实现的是在每个实例中包含以下变量及其值：

   mask:  (as an image which shows the detected object only, like a binary map)
   box: (as a list)
   mask_border_positions (x,y) : (as a list)
   mask_center_position (x,y) :  (as a tuple)

我还具有可视化上面图片的功能，来自官方site：

def display_instances(image, boxes, masks, class_ids, class_names,
                      scores=None, title="",
                      figsize=(16, 16), ax=None,
                      show_mask=True, show_bbox=True,
                      colors=None, captions=None):
    """
    boxes: [num_instance, (y1, x1, y2, x2, class_id)] in image coordinates.
    masks: [height, width, num_instances]
    class_ids: [num_instances]
    class_names: list of class names of the dataset
    scores: (optional) confidence scores for each box
    title: (optional) Figure title
    show_mask, show_bbox: To show masks and bounding boxes or not
    figsize: (optional) the size of the image
    colors: (optional) An array or colors to use with each object
    captions: (optional) A list of strings to use as captions for each object
    """
    # Number of instances
    N = boxes.shape[0]
    if not N:
        print("\n*** No instances to display *** \n")
    else:
        assert boxes.shape[0] == masks.shape[-1] == class_ids.shape[0]

    # If no axis is passed, create one and automatically call show()
    auto_show = False
    if not ax:
        _, ax = plt.subplots(1, figsize=figsize)
        auto_show = True

    # Generate random colors
    colors = colors or random_colors(N)

    # Show area outside image boundaries.
    height, width = image.shape[:2]
    ax.set_ylim(height + 10, -10)
    ax.set_xlim(-10, width + 10)
    ax.axis('off')
    ax.set_title(title)

    masked_image = image.astype(np.uint32).copy()
    for i in range(N):
        color = colors[i]

        # Bounding box
        if not np.any(boxes[i]):
            # Skip this instance. Has no bbox. Likely lost in image cropping.
            continue
        y1, x1, y2, x2 = boxes[i]
        if show_bbox:
            p = patches.Rectangle((x1, y1), x2 - x1, y2 - y1, linewidth=2,
                                alpha=0.7, linestyle="dashed",
                                edgecolor=color, facecolor='none')
            ax.add_patch(p)

        # Label
        if not captions:
            class_id = class_ids[i]
            score = scores[i] if scores is not None else None
            label = class_names[class_id]
            x = random.randint(x1, (x1 + x2) // 2)
            caption = "{} {:.3f}".format(label, score) if score else label
        else:
            caption = captions[i]
        ax.text(x1, y1 + 8, caption,
                color='w', size=11, backgroundcolor="none")

        # Mask
        mask = masks[:, :, i]
        if show_mask:
            masked_image = apply_mask(masked_image, mask, color)

        # Mask Polygon
        # Pad to ensure proper polygons for masks that touch image edges.
        padded_mask = np.zeros(
            (mask.shape[0] + 2, mask.shape[1] + 2), dtype=np.uint8)
        padded_mask[1:-1, 1:-1] = mask
        contours = find_contours(padded_mask, 0.5)
        for verts in contours:
            # Subtract the padding and flip (y, x) to (x, y)
            verts = np.fliplr(verts) - 1
            p = Polygon(verts, facecolor="none", edgecolor=color)
            ax.add_patch(p)
    ax.imshow(masked_image.astype(np.uint8))
    if auto_show:
        plt.show()

下面这些代码段在主体中按如下方式调用：

file_names = glob(os.path.join(IMAGE_DIR, "*.jpg"))
masks_prediction = np.zeros((510, 510, len(file_names)))
for i in range(len(file_names)):
    print(i)
    image = skimage.io.imread(file_names[i])
    predictions = model.detect([image],  verbose=1)
    p = predictions[0]
    masks = p['masks']
    merged_mask = np.zeros((masks.shape[0], masks.shape[1]))
    for j in range(masks.shape[2]):
        merged_mask[masks[:,:,j]==True] = True
        masks_prediction[:,:,i] = merged_mask
print(masks_prediction.shape)

和：

file_names = glob(os.path.join(IMAGE_DIR, "*.jpg"))
class_names = ['BG', 'car', 'traffic_light', 'person']
test_image = skimage.io.imread(file_names[random.randint(0,len(file_names)-1)])
predictions = model.detect([test_image], verbose=1) # We are replicating the same image to fill up the batch_size
p = predictions[0]
visualize.display_instances(test_image, p['rois'], p['masks'], p['class_ids'], 
                            class_names, p['scores'])

我知道这可能是一个琐碎的问题，它们已经存在于代码中的某个地方，但是由于我是一个入门者，所以无法获得蒙版异常值或其中心。如果有一种方法可以按实例获取这些信息，那就太好了。

谢谢。

Answer 1

以下操作正确无误：

masks = p['masks']
class_ids = p['class_ids']
rois = p['rois']
scores = p['scores']
bounding_box = rois[enumerator]

至于轮廓坐标：

def getBoundaryPositions(im):

    class_ids = p['class_ids']  # for usage convenience

    im = im.astype(np.uint8)

    # Find contours:

    (im, contours, hierarchy) = cv2.findContours(im, cv2.RETR_EXTERNAL,
            cv2.CHAIN_APPROX_NONE)
    cnts = contours[0]
    outline_posesXY = np.array([np.append(x[0]) for x in cnts])


    # Calculate image moments of the detected contour
    M = cv2.moments(contours[0])

    # collect pose points (for now only position because we don't have pose) of the center
    positionXY = []
    positionXY.append(round(M['m10'] / M['m00']))
    positionXY.append(round(M['m01'] / M['m00']))


    return (im, positionXY, outline_posesXY)

从Mask_RCNN张量检索信息

1 个答案: