diff --git a/docs/modes/train.md b/docs/modes/train.md index f07c0d9f16..4bf6e4a642 100644 --- a/docs/modes/train.md +++ b/docs/modes/train.md @@ -189,7 +189,7 @@ Training settings for YOLO models refer to the various hyperparameters and confi | `project` | `None` | project name | | `name` | `None` | experiment name | | `exist_ok` | `False` | whether to overwrite existing experiment | -| `pretrained` | `True` | (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str) | +| `pretrained` | `True` | (bool \| str) whether to use a pretrained model (bool) or a model to load weights from (str) | | `optimizer` | `'auto'` | optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto] | | `verbose` | `False` | whether to print verbose output | | `seed` | `0` | random seed for reproducibility | @@ -202,7 +202,7 @@ Training settings for YOLO models refer to the various hyperparameters and confi | `amp` | `True` | Automatic Mixed Precision (AMP) training, choices=[True, False] | | `fraction` | `1.0` | dataset fraction to train on (default is 1.0, all images in train set) | | `profile` | `False` | profile ONNX and TensorRT speeds during training for loggers | -| `freeze` | `None` | (int or list, optional) freeze first n layers, or freeze list of layer indices during training | +| `freeze` | `None` | (int \| list, optional) freeze first n layers, or freeze list of layer indices during training | | `lr0` | `0.01` | initial learning rate (i.e. SGD=1E-2, Adam=1E-3) | | `lrf` | `0.01` | final learning rate (lr0 * lrf) | | `momentum` | `0.937` | SGD momentum/Adam beta1 | diff --git a/docs/usage/cfg.md b/docs/usage/cfg.md index 7ff9867d43..0dc872c9ca 100644 --- a/docs/usage/cfg.md +++ b/docs/usage/cfg.md @@ -88,7 +88,7 @@ The training settings for YOLO models encompass various hyperparameters and conf | `project` | `None` | project name | | `name` | `None` | experiment name | | `exist_ok` | `False` | whether to overwrite existing experiment | -| `pretrained` | `True` | (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str) | +| `pretrained` | `True` | (bool \| str) whether to use a pretrained model (bool) or a model to load weights from (str) | | `optimizer` | `'auto'` | optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto] | | `verbose` | `False` | whether to print verbose output | | `seed` | `0` | random seed for reproducibility | @@ -101,7 +101,7 @@ The training settings for YOLO models encompass various hyperparameters and conf | `amp` | `True` | Automatic Mixed Precision (AMP) training, choices=[True, False] | | `fraction` | `1.0` | dataset fraction to train on (default is 1.0, all images in train set) | | `profile` | `False` | profile ONNX and TensorRT speeds during training for loggers | -| `freeze` | `None` | (int or list, optional) freeze first n layers, or freeze list of layer indices during training | +| `freeze` | `None` | (int \| list, optional) freeze first n layers, or freeze list of layer indices during training | | `lr0` | `0.01` | initial learning rate (i.e. SGD=1E-2, Adam=1E-3) | | `lrf` | `0.01` | final learning rate (lr0 * lrf) | | `momentum` | `0.937` | SGD momentum/Adam beta1 | diff --git a/examples/YOLOv8-Region-Counter/readme.md b/examples/YOLOv8-Region-Counter/readme.md index 2ce093aa29..da303f1946 100644 --- a/examples/YOLOv8-Region-Counter/readme.md +++ b/examples/YOLOv8-Region-Counter/readme.md @@ -5,8 +5,8 @@

- - + +        

@@ -42,6 +42,9 @@ After the video begins playing, you can freely move the region anywhere within t # If you want to save results python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --view-img +# If you want to run model on CPU +python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --view-img --device cpu + # If you want to change model file python yolov8_region_counter.py --source "path/to/video.mp4" --save-img --weights "path/to/model.pt" @@ -52,10 +55,12 @@ python yolov8_region_counter.py --source "path/to/video.mp4" --view-img ## Usage Options - `--source`: Specifies the path to the video file you want to run inference on. +- `--device`: Specifies the device `cpu` or `0` - `--save-img`: Flag to save the detection results as images. - `--weights`: Specifies a different YOLOv8 model file (e.g., `yolov8n.pt`, `yolov8s.pt`, `yolov8m.pt`, `yolov8l.pt`, `yolov8x.pt`). - `--line-thickness`: Specifies the bounding box thickness -- `--region-thickness`: Specific the region boxes thickness +- `--region-thickness`: Specifies the region boxes thickness +- `--track-thickness`: Specifies the track line thickness ## FAQ @@ -63,11 +68,40 @@ python yolov8_region_counter.py --source "path/to/video.mp4" --view-img Region counting is a computational method utilized to ascertain the quantity of objects within a specific area in recorded video or real-time streams. This technique finds frequent application in image processing, computer vision, and pattern recognition, facilitating the analysis and segmentation of objects or features based on their spatial relationships. -**2. Why Combine Region Counting with YOLOv8?** +**2. Is Friendly Region Plotting Supported by the Region Counter?** + +The Region Counter offers the capability to create regions in various formats, such as polygons and rectangles. You have the flexibility to modify region attributes, including coordinates, colors, and other details, as demonstrated in the following code: + +```python +counting_regions = [ + { + "name": "YOLOv8 Polygon Region", + "polygon": Polygon( + [(50, 80), (250, 20), (450, 80), (400, 350), (100, 350)] + ), # Polygon with five points (Pentagon) + "counts": 0, + "dragging": False, + "region_color": (255, 42, 4), # BGR Value + "text_color": (255, 255, 255), # Region Text Color + }, + { + "name": "YOLOv8 Rectangle Region", + "polygon": Polygon( + [(200, 250), (440, 250), (440, 550), (200, 550)] + ), # Rectangle with four points + "counts": 0, + "dragging": False, + "region_color": (37, 255, 225), # BGR Value + "text_color": (0, 0, 0), # Region Text Color + }, +] +``` + +**3. Why Combine Region Counting with YOLOv8?** YOLOv8 specializes in the detection and tracking of objects in video streams. Region counting complements this by enabling object counting within designated areas, making it a valuable application of YOLOv8. -**3. How Can I Troubleshoot Issues?** +**4. How Can I Troubleshoot Issues?** To gain more insights during inference, you can include the `--debug` flag in your command: @@ -75,10 +109,10 @@ To gain more insights during inference, you can include the `--debug` flag in yo python yolov8_region_counter.py --source "path to video file" --debug ``` -**4. Can I Employ Other YOLO Versions?** +**5. Can I Employ Other YOLO Versions?** Certainly, you have the flexibility to specify different YOLO model weights using the `--weights` option. -**5. Where Can I Access Additional Information?** +**6. Where Can I Access Additional Information?** For a comprehensive guide on using YOLOv8 with Object Tracking, please refer to [Multi-Object Tracking with Ultralytics YOLO](https://docs.ultralytics.com/modes/track/). diff --git a/examples/YOLOv8-Region-Counter/yolov8_region_counter.py b/examples/YOLOv8-Region-Counter/yolov8_region_counter.py index 07567e557b..bdc4013201 100644 --- a/examples/YOLOv8-Region-Counter/yolov8_region_counter.py +++ b/examples/YOLOv8-Region-Counter/yolov8_region_counter.py @@ -4,34 +4,37 @@ from pathlib import Path import cv2 import numpy as np +from shapely.geometry import Polygon +from shapely.geometry.point import Point from ultralytics import YOLO - -track_history = defaultdict(lambda: []) - from ultralytics.utils.files import increment_path from ultralytics.utils.plotting import Annotator, colors -# Region utils +track_history = defaultdict(lambda: []) + current_region = None -counting_regions = [{ - 'name': 'YOLOv8 Region A', - 'roi': (50, 100, 240, 300), - 'counts': 0, - 'dragging': False, - 'region_color': (0, 255, 0)}, { - 'name': 'YOLOv8 Region B', - 'roi': (200, 250, 240, 300), +counting_regions = [ + { + 'name': 'YOLOv8 Polygon Region', + 'polygon': Polygon([(50, 80), (250, 20), (450, 80), (400, 350), (100, 350)]), # Polygon points + 'counts': 0, + 'dragging': False, + 'region_color': (255, 42, 4), # BGR Value + 'text_color': (255, 255, 255) # Region Text Color + }, + { + 'name': 'YOLOv8 Rectangle Region', + 'polygon': Polygon([(200, 250), (440, 250), (440, 550), (200, 550)]), # Polygon points 'counts': 0, 'dragging': False, - 'region_color': (255, 144, 31)}] + 'region_color': (37, 255, 225), # BGR Value + 'text_color': (0, 0, 0), # Region Text Color + }, ] -def is_inside_roi(box, roi): - """Compare bbox with region box.""" - x, y, _, _ = box - roi_x, roi_y, roi_w, roi_h = roi - return roi_x < x < roi_x + roi_w and roi_y < y < roi_y + roi_h +def is_inside_polygon(point, polygon): + return polygon.contains(Point(point)) def mouse_callback(event, x, y, flags, param): @@ -41,18 +44,21 @@ def mouse_callback(event, x, y, flags, param): # Mouse left button down event if event == cv2.EVENT_LBUTTONDOWN: for region in counting_regions: - roi_x, roi_y, roi_w, roi_h = region['roi'] - if roi_x < x < roi_x + roi_w and roi_y < y < roi_y + roi_h: + if is_inside_polygon((x, y), region['polygon']): current_region = region current_region['dragging'] = True - current_region['offset_x'] = x - roi_x - current_region['offset_y'] = y - roi_y + current_region['offset_x'] = x + current_region['offset_y'] = y # Mouse move event elif event == cv2.EVENT_MOUSEMOVE: if current_region is not None and current_region['dragging']: - current_region['roi'] = (x - current_region['offset_x'], y - current_region['offset_y'], - current_region['roi'][2], current_region['roi'][3]) + dx = x - current_region['offset_x'] + dy = y - current_region['offset_y'] + current_region['polygon'] = Polygon([ + (p[0] + dx, p[1] + dy) for p in current_region['polygon'].exterior.coords]) + current_region['offset_x'] = x + current_region['offset_y'] = y # Mouse left button up event elif event == cv2.EVENT_LBUTTONUP: @@ -60,26 +66,33 @@ def mouse_callback(event, x, y, flags, param): current_region['dragging'] = False -def run(weights='yolov8n.pt', - source='test.mp4', - view_img=False, - save_img=False, - exist_ok=False, - line_thickness=2, - region_thickness=2): +def run( + weights='yolov8n.pt', + source=None, + device='cpu', + view_img=False, + save_img=False, + exist_ok=False, + line_thickness=2, + track_thickness=2, + region_thickness=2, +): """ Run Region counting on a video using YOLOv8 and ByteTrack. Supports movable region for real time counting inside specific area. Supports multiple regions counting. + Regions can be Polygons or rectangle in shape Args: weights (str): Model weights path. source (str): Video file path. + device (str): processing device cpu, 0, 1 view_img (bool): Show results. save_img (bool): Save results. exist_ok (bool): Overwrite existing files. line_thickness (int): Bounding box thickness. + track_thickness (int): Tracking line thickness region_thickness (int): Region thickness. """ vid_frame_count = 0 @@ -90,6 +103,7 @@ def run(weights='yolov8n.pt', # Setup Model model = YOLO(f'{weights}') + model.to('cuda') if device == '0' else model.to('cpu') # Video setup videocapture = cv2.VideoCapture(source) @@ -122,40 +136,43 @@ def run(weights='yolov8n.pt', label = str(names[cls]) xyxy = (x - w / 2), (y - h / 2), (x + w / 2), (y + h / 2) - # Bounding box + # Bounding box plot bbox_color = colors(cls, True) annotator.box_label(xyxy, label, color=bbox_color) - # Tracking Lines + # Tracking Lines plot track = track_history[track_id] track.append((float(x), float(y))) if len(track) > 30: track.pop(0) points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) - cv2.polylines(frame, [points], isClosed=False, color=bbox_color, thickness=line_thickness) + cv2.polylines(frame, [points], isClosed=False, color=bbox_color, thickness=track_thickness) - # Check If detection inside region + # Check if detection inside region for region in counting_regions: - if is_inside_roi(box, region['roi']): + if is_inside_polygon((x, y), region['polygon']): region['counts'] += 1 - # Draw region boxes + # Draw regions (Polygons/Rectangles) for region in counting_regions: region_label = str(region['counts']) - roi_x, roi_y, roi_w, roi_h = region['roi'] region_color = region['region_color'] - center_x = roi_x + roi_w // 2 - center_y = roi_y + roi_h // 2 - text_margin = 15 - - # Region plotting - cv2.rectangle(frame, (roi_x, roi_y), (roi_x + roi_w, roi_y + roi_h), region_color, region_thickness) - t_size, _ = cv2.getTextSize(region_label, cv2.FONT_HERSHEY_SIMPLEX, fontScale=1.0, thickness=line_thickness) - text_x = center_x - t_size[0] // 2 - text_margin - text_y = center_y + t_size[1] // 2 + text_margin - cv2.rectangle(frame, (text_x - text_margin, text_y - t_size[1] - text_margin), - (text_x + t_size[0] + text_margin, text_y + text_margin), region_color, -1) - cv2.putText(frame, region_label, (text_x, text_y), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), line_thickness) + region_text_color = region['text_color'] + + polygon_coords = np.array(region['polygon'].exterior.coords, dtype=np.int32) + centroid_x, centroid_y = int(region['polygon'].centroid.x), int(region['polygon'].centroid.y) + + text_size, _ = cv2.getTextSize(region_label, + cv2.FONT_HERSHEY_SIMPLEX, + fontScale=0.7, + thickness=line_thickness) + text_x = centroid_x - text_size[0] // 2 + text_y = centroid_y + text_size[1] // 2 + cv2.rectangle(frame, (text_x - 5, text_y - text_size[1] - 5), (text_x + text_size[0] + 5, text_y + 5), + region_color, -1) + cv2.putText(frame, region_label, (text_x, text_y), cv2.FONT_HERSHEY_SIMPLEX, 0.7, region_text_color, + line_thickness) + cv2.polylines(frame, [polygon_coords], isClosed=True, color=region_color, thickness=region_thickness) if view_img: if vid_frame_count == 1: @@ -182,12 +199,15 @@ def parse_opt(): """Parse command line arguments.""" parser = argparse.ArgumentParser() parser.add_argument('--weights', type=str, default='yolov8n.pt', help='initial weights path') + parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') parser.add_argument('--source', type=str, required=True, help='video file path') parser.add_argument('--view-img', action='store_true', help='show results') parser.add_argument('--save-img', action='store_true', help='save results') parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') parser.add_argument('--line-thickness', type=int, default=2, help='bounding box thickness') + parser.add_argument('--track-thickness', type=int, default=2, help='Tracking line thickness') parser.add_argument('--region-thickness', type=int, default=4, help='Region thickness') + return parser.parse_args() diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index 83e43fb54a..6bdf75c357 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license -__version__ = '8.0.182' +__version__ = '8.0.183' from ultralytics.models import RTDETR, SAM, YOLO from ultralytics.models.fastsam import FastSAM diff --git a/ultralytics/utils/checks.py b/ultralytics/utils/checks.py index ddd6ccc8e7..1327b7a79b 100644 --- a/ultralytics/utils/checks.py +++ b/ultralytics/utils/checks.py @@ -493,9 +493,15 @@ def collect_system_info(): f"{'CPU':<20}{get_cpu_info()}\n" f"{'CUDA':<20}{torch.version.cuda if torch and torch.cuda.is_available() else None}\n") - for r in parse_requirements(): + if (ROOT.parent / 'requirements.txt').exists(): # pip install + requirements = parse_requirements() + else: # git install + from pkg_resources import get_distribution + requirements = get_distribution('ultralytics').requires() + + for r in requirements: current = version(r.name) - is_met = '✅ ' if check_version(current, r.specifier) else '❌ ' + is_met = '✅ ' if check_version(current, str(r.specifier)) else '❌ ' LOGGER.info(f'{r.name:<20}{is_met}{current}{r.specifier}') diff --git a/ultralytics/utils/tuner.py b/ultralytics/utils/tuner.py index 2ca6e5a30a..5bccd6fe4d 100644 --- a/ultralytics/utils/tuner.py +++ b/ultralytics/utils/tuner.py @@ -124,7 +124,7 @@ def run_ray_tune(model, tuner_callbacks = [WandbLoggerCallback(project='YOLOv8-tune')] if wandb else [] # Create the Ray Tune hyperparameter search tuner - tune_dir = get_save_dir(DEFAULT_CFG, name='tune') + tune_dir = get_save_dir(DEFAULT_CFG, name='tune').resolve() # must be absolute dir tune_dir.mkdir(parents=True, exist_ok=True) tuner = tune.Tuner(trainable_with_resources, param_space=space,