Reference for ultralytics/utils/plotting.py

class Colors:
    """
    Ultralytics default color palette https://ultralytics.com/.

    This class provides methods to work with the Ultralytics color palette, including converting hex color codes to
    RGB values.

    Attributes:
        palette (list of tuple): List of RGB color values.
        n (int): The number of colors in the palette.
        pose_palette (np.array): A specific color palette array with dtype np.uint8.
    """

    def __init__(self):
        """Initialize colors as hex = matplotlib.colors.TABLEAU_COLORS.values()."""
        hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
                '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
        self.palette = [self.hex2rgb(f'#{c}') for c in hexs]
        self.n = len(self.palette)
        self.pose_palette = np.array([[255, 128, 0], [255, 153, 51], [255, 178, 102], [230, 230, 0], [255, 153, 255],
                                      [153, 204, 255], [255, 102, 255], [255, 51, 255], [102, 178, 255], [51, 153, 255],
                                      [255, 153, 153], [255, 102, 102], [255, 51, 51], [153, 255, 153], [102, 255, 102],
                                      [51, 255, 51], [0, 255, 0], [0, 0, 255], [255, 0, 0], [255, 255, 255]],
                                     dtype=np.uint8)

    def __call__(self, i, bgr=False):
        """Converts hex color codes to RGB values."""
        c = self.palette[int(i) % self.n]
        return (c[2], c[1], c[0]) if bgr else c

    @staticmethod
    def hex2rgb(h):
        """Converts hex color codes to RGB values (i.e. default PIL order)."""
        return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))

class Annotator:
    """
    Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations.

    Attributes:
        im (Image.Image or numpy array): The image to annotate.
        pil (bool): Whether to use PIL or cv2 for drawing annotations.
        font (ImageFont.truetype or ImageFont.load_default): Font used for text annotations.
        lw (float): Line width for drawing.
        skeleton (List[List[int]]): Skeleton structure for keypoints.
        limb_color (List[int]): Color palette for limbs.
        kpt_color (List[int]): Color palette for keypoints.
    """

    def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
        """Initialize the Annotator class with image and line width along with color palette for keypoints and limbs."""
        assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
        non_ascii = not is_ascii(example)  # non-latin labels, i.e. asian, arabic, cyrillic
        self.pil = pil or non_ascii
        self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2)  # line width
        if self.pil:  # use PIL
            self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
            self.draw = ImageDraw.Draw(self.im)
            try:
                font = check_font('Arial.Unicode.ttf' if non_ascii else font)
                size = font_size or max(round(sum(self.im.size) / 2 * 0.035), 12)
                self.font = ImageFont.truetype(str(font), size)
            except Exception:
                self.font = ImageFont.load_default()
            # Deprecation fix for w, h = getsize(string) -> _, _, w, h = getbox(string)
            if check_version(pil_version, '9.2.0'):
                self.font.getsize = lambda x: self.font.getbbox(x)[2:4]  # text width, height
        else:  # use cv2
            self.im = im
            self.tf = max(self.lw - 1, 1)  # font thickness
            self.sf = self.lw / 3  # font scale
        # Pose
        self.skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12], [7, 13], [6, 7], [6, 8], [7, 9],
                         [8, 10], [9, 11], [2, 3], [1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]

        self.limb_color = colors.pose_palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]]
        self.kpt_color = colors.pose_palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]]

    def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
        """Add one xyxy box to image with label."""
        if isinstance(box, torch.Tensor):
            box = box.tolist()
        if self.pil or not is_ascii(label):
            self.draw.rectangle(box, width=self.lw, outline=color)  # box
            if label:
                w, h = self.font.getsize(label)  # text width, height
                outside = box[1] - h >= 0  # label fits outside box
                self.draw.rectangle(
                    (box[0], box[1] - h if outside else box[1], box[0] + w + 1,
                     box[1] + 1 if outside else box[1] + h + 1),
                    fill=color,
                )
                # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
                self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
        else:  # cv2
            p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
            cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
            if label:
                w, h = cv2.getTextSize(label, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
                outside = p1[1] - h >= 3
                p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
                cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
                cv2.putText(self.im,
                            label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2),
                            0,
                            self.sf,
                            txt_color,
                            thickness=self.tf,
                            lineType=cv2.LINE_AA)

    def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False):
        """
        Plot masks on image.

        Args:
            masks (tensor): Predicted masks on cuda, shape: [n, h, w]
            colors (List[List[Int]]): Colors for predicted masks, [[r, g, b] * n]
            im_gpu (tensor): Image is in cuda, shape: [3, h, w], range: [0, 1]
            alpha (float): Mask transparency: 0.0 fully transparent, 1.0 opaque
            retina_masks (bool): Whether to use high resolution masks or not. Defaults to False.
        """
        if self.pil:
            # Convert to numpy first
            self.im = np.asarray(self.im).copy()
        if len(masks) == 0:
            self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
        if im_gpu.device != masks.device:
            im_gpu = im_gpu.to(masks.device)
        colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
        colors = colors[:, None, None]  # shape(n,1,1,3)
        masks = masks.unsqueeze(3)  # shape(n,h,w,1)
        masks_color = masks * (colors * alpha)  # shape(n,h,w,3)

        inv_alph_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
        mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)

        im_gpu = im_gpu.flip(dims=[0])  # flip channel
        im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
        im_gpu = im_gpu * inv_alph_masks[-1] + mcs
        im_mask = (im_gpu * 255)
        im_mask_np = im_mask.byte().cpu().numpy()
        self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
        if self.pil:
            # Convert im back to PIL and update draw
            self.fromarray(self.im)

    def kpts(self, kpts, shape=(640, 640), radius=5, kpt_line=True):
        """
        Plot keypoints on the image.

        Args:
            kpts (tensor): Predicted keypoints with shape [17, 3]. Each keypoint has (x, y, confidence).
            shape (tuple): Image shape as a tuple (h, w), where h is the height and w is the width.
            radius (int, optional): Radius of the drawn keypoints. Default is 5.
            kpt_line (bool, optional): If True, the function will draw lines connecting keypoints
                                       for human pose. Default is True.

        Note: `kpt_line=True` currently only supports human pose plotting.
        """
        if self.pil:
            # Convert to numpy first
            self.im = np.asarray(self.im).copy()
        nkpt, ndim = kpts.shape
        is_pose = nkpt == 17 and ndim == 3
        kpt_line &= is_pose  # `kpt_line=True` for now only supports human pose plotting
        for i, k in enumerate(kpts):
            color_k = [int(x) for x in self.kpt_color[i]] if is_pose else colors(i)
            x_coord, y_coord = k[0], k[1]
            if x_coord % shape[1] != 0 and y_coord % shape[0] != 0:
                if len(k) == 3:
                    conf = k[2]
                    if conf < 0.5:
                        continue
                cv2.circle(self.im, (int(x_coord), int(y_coord)), radius, color_k, -1, lineType=cv2.LINE_AA)

        if kpt_line:
            ndim = kpts.shape[-1]
            for i, sk in enumerate(self.skeleton):
                pos1 = (int(kpts[(sk[0] - 1), 0]), int(kpts[(sk[0] - 1), 1]))
                pos2 = (int(kpts[(sk[1] - 1), 0]), int(kpts[(sk[1] - 1), 1]))
                if ndim == 3:
                    conf1 = kpts[(sk[0] - 1), 2]
                    conf2 = kpts[(sk[1] - 1), 2]
                    if conf1 < 0.5 or conf2 < 0.5:
                        continue
                if pos1[0] % shape[1] == 0 or pos1[1] % shape[0] == 0 or pos1[0] < 0 or pos1[1] < 0:
                    continue
                if pos2[0] % shape[1] == 0 or pos2[1] % shape[0] == 0 or pos2[0] < 0 or pos2[1] < 0:
                    continue
                cv2.line(self.im, pos1, pos2, [int(x) for x in self.limb_color[i]], thickness=2, lineType=cv2.LINE_AA)
        if self.pil:
            # Convert im back to PIL and update draw
            self.fromarray(self.im)

    def rectangle(self, xy, fill=None, outline=None, width=1):
        """Add rectangle to image (PIL-only)."""
        self.draw.rectangle(xy, fill, outline, width)

    def text(self, xy, text, txt_color=(255, 255, 255), anchor='top', box_style=False):
        """Adds text to an image using PIL or cv2."""
        if anchor == 'bottom':  # start y from font bottom
            w, h = self.font.getsize(text)  # text width, height
            xy[1] += 1 - h
        if self.pil:
            if box_style:
                w, h = self.font.getsize(text)
                self.draw.rectangle((xy[0], xy[1], xy[0] + w + 1, xy[1] + h + 1), fill=txt_color)
                # Using `txt_color` for background and draw fg with white color
                txt_color = (255, 255, 255)
            if '\n' in text:
                lines = text.split('\n')
                _, h = self.font.getsize(text)
                for line in lines:
                    self.draw.text(xy, line, fill=txt_color, font=self.font)
                    xy[1] += h
            else:
                self.draw.text(xy, text, fill=txt_color, font=self.font)
        else:
            if box_style:
                w, h = cv2.getTextSize(text, 0, fontScale=self.sf, thickness=self.tf)[0]  # text width, height
                outside = xy[1] - h >= 3
                p2 = xy[0] + w, xy[1] - h - 3 if outside else xy[1] + h + 3
                cv2.rectangle(self.im, xy, p2, txt_color, -1, cv2.LINE_AA)  # filled
                # Using `txt_color` for background and draw fg with white color
                txt_color = (255, 255, 255)
            cv2.putText(self.im, text, xy, 0, self.sf, txt_color, thickness=self.tf, lineType=cv2.LINE_AA)

    def fromarray(self, im):
        """Update self.im from a numpy array."""
        self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
        self.draw = ImageDraw.Draw(self.im)

    def result(self):
        """Return annotated image as array."""
        return np.asarray(self.im)