Import Annotator class from ultralytics package (#11930)

* Import Annotator class from `ultralytics` package

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Import Annotator class from `ultralytics` package

* Update requirements.txt

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

---------

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

classify/predict.py

@@ -43,12 +43,13 @@ if str(ROOT) not in sys.path:
     sys.path.append(str(ROOT))  # add ROOT to PATH
 ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
+from ultralytics.utils.plotting import Annotator
+
 from models.common import DetectMultiBackend
 from utils.augmentations import classify_transforms
 from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
 from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                            increment_path, print_args, strip_optimizer)
-from utils.plots import Annotator
 from utils.torch_utils import select_device, smart_inference_mode
 
 
@@ -144,7 +145,7 @@ def run(
             # Write results
             text = '\n'.join(f'{prob[j]:.2f} {names[j]}' for j in top5i)
             if save_img or view_img:  # Add bbox to image
-                annotator.text((32, 32), text, txt_color=(255, 255, 255))
+                annotator.text([32, 32], text, txt_color=(255, 255, 255))
             if save_txt:  # Write to file
                 with open(f'{txt_path}.txt', 'a') as f:
                     f.write(text + '\n')

detect.py

@@ -42,11 +42,12 @@ if str(ROOT) not in sys.path:
     sys.path.append(str(ROOT))  # add ROOT to PATH
 ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
+
 from models.common import DetectMultiBackend
 from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
 from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                            increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
-from utils.plots import Annotator, colors, save_one_box
 from utils.torch_utils import select_device, smart_inference_mode
 
 

models/common.py

@@ -23,13 +23,13 @@ import torch
 import torch.nn as nn
 from PIL import Image
 from torch.cuda import amp
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
 
 from utils import TryExcept
 from utils.dataloaders import exif_transpose, letterbox
 from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
                            increment_path, is_jupyter, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy,
                            xyxy2xywh, yaml_load)
-from utils.plots import Annotator, colors, save_one_box
 from utils.torch_utils import copy_attr, smart_inference_mode
 
 

requirements.txt

@@ -15,7 +15,7 @@ thop>=0.1.1  # FLOPs computation
 torch>=1.7.0  # see https://pytorch.org/get-started/locally (recommended)
 torchvision>=0.8.1
 tqdm>=4.64.0
-ultralytics>=8.0.145
+ultralytics>=8.0.146
 # protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012
 
 # Logging ---------------------------------------------------------------------

segment/predict.py

@@ -42,12 +42,13 @@ if str(ROOT) not in sys.path:
     sys.path.append(str(ROOT))  # add ROOT to PATH
 ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
+
 from models.common import DetectMultiBackend
 from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
 from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                            increment_path, non_max_suppression, print_args, scale_boxes, scale_segments,
                            strip_optimizer)
-from utils.plots import Annotator, colors, save_one_box
 from utils.segment.general import masks2segments, process_mask, process_mask_native
 from utils.torch_utils import select_device, smart_inference_mode
 

utils/loggers/clearml/clearml_utils.py

@@ -5,8 +5,7 @@ from pathlib import Path
 
 import numpy as np
 import yaml
-
+from ultralytics.utils.plotting import Annotator, colors
-from utils.plots import Annotator, colors
 
 try:
     import clearml

utils/plots.py

@@ -8,7 +8,6 @@ import math
 import os
 from copy import copy
 from pathlib import Path
-from urllib.error import URLError
 
 import cv2
 import matplotlib
@@ -17,14 +16,13 @@ import numpy as np
 import pandas as pd
 import seaborn as sn
 import torch
-from PIL import Image, ImageDraw, ImageFont
+from PIL import Image, ImageDraw
 from scipy.ndimage.filters import gaussian_filter1d
+from ultralytics.utils.plotting import Annotator
 
 from utils import TryExcept, threaded
-from utils.general import (CONFIG_DIR, FONT, LOGGER, check_font, check_requirements, clip_boxes, increment_path,
+from utils.general import LOGGER, clip_boxes, increment_path, xywh2xyxy, xyxy2xywh
-                           is_ascii, xywh2xyxy, xyxy2xywh)
 from utils.metrics import fitness
-from utils.segment.general import scale_image
 
 # Settings
 RANK = int(os.getenv('RANK', -1))
@@ -53,120 +51,6 @@ class Colors:
 colors = Colors()  # create instance for 'from utils.plots import colors'
 
 
-def check_pil_font(font=FONT, size=10):
-    # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary
-    font = Path(font)
-    font = font if font.exists() else (CONFIG_DIR / font.name)
-    try:
-        return ImageFont.truetype(str(font) if font.exists() else font.name, size)
-    except Exception:  # download if missing
-        try:
-            check_font(font)
-            return ImageFont.truetype(str(font), size)
-        except TypeError:
-            check_requirements('Pillow>=8.4.0')  # known issue https://github.com/ultralytics/yolov5/issues/5374
-        except URLError:  # not online
-            return ImageFont.load_default()
-
-
-class Annotator:
-    # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations
-    def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
-        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
-        if self.pil:  # use PIL
-            self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
-            self.draw = ImageDraw.Draw(self.im)
-            self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font,
-                                       size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
-        else:  # use cv2
-            self.im = im
-        self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2)  # line width
-
-    def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
-        # Add one xyxy box to image with label
-        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 (WARNING: deprecated) in 9.2.0
-                # _, _, w, h = self.font.getbbox(label)  # text width, height (New)
-                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:
-                tf = max(self.lw - 1, 1)  # font thickness
-                w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=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.lw / 3,
-                            txt_color,
-                            thickness=tf,
-                            lineType=cv2.LINE_AA)
-
-    def masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False):
-        """Plot masks at once.
-        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): img is in cuda, shape: [3, h, w], range: [0, 1]
-            alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque
-        """
-        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
-        colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0
-        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 * inv_alph_masks).sum(0) * 2  # mask color summand 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).byte().cpu().numpy()
-        self.im[:] = im_mask if retina_masks else scale_image(im_gpu.shape, im_mask, self.im.shape)
-        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'):
-        # Add text to image (PIL-only)
-        if anchor == 'bottom':  # start y from font bottom
-            w, h = self.font.getsize(text)  # text width, height
-            xy[1] += 1 - h
-        self.draw.text(xy, text, fill=txt_color, font=self.font)
-
-    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)
-
-
 def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
     """
     x:              Features to be visualized
@@ -266,7 +150,7 @@ def plot_images(images, targets, paths=None, fname='images.jpg', names=None):
         x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
         annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2)  # borders
         if paths:
-            annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
+            annotator.text([x + 5, y + 5], text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
         if len(targets) > 0:
             ti = targets[targets[:, 0] == i]  # image targets
             boxes = xywh2xyxy(ti[:, 2:6]).T

utils/segment/plots.py

@@ -54,7 +54,7 @@ def plot_images_and_masks(images, targets, masks, paths=None, fname='images.jpg'
         x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
         annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2)  # borders
         if paths:
-            annotator.text((x + 5, y + 5), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
+            annotator.text([x + 5, y + 5], text=Path(paths[i]).name[:40], txt_color=(220, 220, 220))  # filenames
         if len(targets) > 0:
             idx = targets[:, 0] == i
             ti = targets[idx]  # image targets