New `ASSETS` and trackers GMC cleanup (#4425)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

docs/reference/data/converter.md

@@ -13,6 +13,10 @@ keywords: Ultralytics, Data Converter, coco91_to_coco80_class, merge_multi_segme
 ## ::: ultralytics.data.converter.coco91_to_coco80_class
 <br><br>
 
+---
+## ::: ultralytics.data.converter.coco80_to_coco91_class
+<br><br>
+
 ---
 ## ::: ultralytics.data.converter.convert_coco
 <br><br>

docs/reference/utils/files.md

@@ -36,7 +36,3 @@ keywords: Ultralytics, utility functions, file operations, working directory, fi
 ---
 ## ::: ultralytics.utils.files.get_latest_run
 <br><br>
-
----
-## ::: ultralytics.utils.files.make_dirs
-<br><br>

docs/reference/utils/ops.md

@@ -13,10 +13,6 @@ keywords: Ultralytics YOLO, Utility Operations, segment2box, make_divisible, cli
 ## ::: ultralytics.utils.ops.Profile
 <br><br>
 
----
-## ::: ultralytics.utils.ops.coco80_to_coco91_class
-<br><br>
-
 ---
 ## ::: ultralytics.utils.ops.segment2box
 <br><br>

examples/YOLOv8-ONNXRuntime/main.py

@@ -5,7 +5,7 @@ import numpy as np
 import onnxruntime as ort
 import torch
 
-from ultralytics.utils import ROOT, yaml_load
+from ultralytics.utils import ASSETS, yaml_load
 from ultralytics.utils.checks import check_requirements, check_yaml
 
 
@@ -198,17 +198,14 @@ class Yolov8:
         outputs = session.run(None, {model_inputs[0].name: img_data})
 
         # Perform post-processing on the outputs to obtain output image.
-        output_img = self.postprocess(self.img, outputs)
+        return self.postprocess(self.img, outputs)  # output image
-
-        # Return the resulting output image
-        return output_img
 
 
 if __name__ == '__main__':
     # Create an argument parser to handle command-line arguments
     parser = argparse.ArgumentParser()
     parser.add_argument('--model', type=str, default='yolov8n.onnx', help='Input your ONNX model.')
-    parser.add_argument('--img', type=str, default=str(ROOT / 'assets/bus.jpg'), help='Path to input image.')
+    parser.add_argument('--img', type=str, default=str(ASSETS / 'bus.jpg'), help='Path to input image.')
     parser.add_argument('--conf-thres', type=float, default=0.5, help='Confidence threshold')
     parser.add_argument('--iou-thres', type=float, default=0.5, help='NMS IoU threshold')
     args = parser.parse_args()

examples/YOLOv8-OpenCV-ONNX-Python/main.py

@@ -3,7 +3,7 @@ import argparse
 import cv2.dnn
 import numpy as np
 
-from ultralytics.utils import ROOT, yaml_load
+from ultralytics.utils import ASSETS, yaml_load
 from ultralytics.utils.checks import check_yaml
 
 CLASSES = yaml_load(check_yaml('coco128.yaml'))['names']
@@ -75,6 +75,6 @@ def main(onnx_model, input_image):
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--model', default='yolov8n.onnx', help='Input your onnx model.')
-    parser.add_argument('--img', default=str(ROOT / 'assets/bus.jpg'), help='Path to input image.')
+    parser.add_argument('--img', default=str(ASSETS / 'bus.jpg'), help='Path to input image.')
     args = parser.parse_args()
     main(args.model, args.img)

tests/test_cli.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 import pytest
 
-from ultralytics.utils import ROOT, SETTINGS
+from ultralytics.utils import ASSETS, SETTINGS
 
 WEIGHTS_DIR = Path(SETTINGS['weights_dir'])
 TASK_ARGS = [
@@ -40,12 +40,12 @@ def test_train(task, model, data):
 
 @pytest.mark.parametrize('task,model,data', TASK_ARGS)
 def test_val(task, model, data):
-    run(f'yolo val {task} model={WEIGHTS_DIR / model}.pt data={data} imgsz=32')
+    run(f'yolo val {task} model={WEIGHTS_DIR / model}.pt data={data} imgsz=32 save_txt save_json')
 
 
 @pytest.mark.parametrize('task,model,data', TASK_ARGS)
 def test_predict(task, model, data):
-    run(f"yolo predict model={WEIGHTS_DIR / model}.pt source={ROOT / 'assets'} imgsz=32 save save_crop save_txt")
+    run(f'yolo predict model={WEIGHTS_DIR / model}.pt source={ASSETS} imgsz=32 save save_crop save_txt')
 
 
 @pytest.mark.parametrize('model,format', EXPORT_ARGS)
@@ -56,11 +56,11 @@ def test_export(model, format):
 def test_rtdetr(task='detect', model='yolov8n-rtdetr.yaml', data='coco8.yaml'):
     # Warning: MUST use imgsz=640
     run(f'yolo train {task} model={model} data={data} imgsz=640 epochs=1 cache=disk')
-    run(f"yolo predict {task} model={model} source={ROOT / 'assets/bus.jpg'} imgsz=640 save save_crop save_txt")
+    run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=640 save save_crop save_txt")
 
 
 def test_fastsam(task='segment', model=WEIGHTS_DIR / 'FastSAM-s.pt', data='coco8-seg.yaml'):
-    source = ROOT / 'assets/bus.jpg'
+    source = ASSETS / 'bus.jpg'
 
     run(f'yolo segment val {task} model={model} data={data} imgsz=32')
     run(f'yolo segment predict model={model} source={source} imgsz=32 save save_crop save_txt')
@@ -98,7 +98,7 @@ def test_mobilesam():
     model = SAM(WEIGHTS_DIR / 'mobile_sam.pt')
 
     # Source
-    source = ROOT / 'assets/zidane.jpg'
+    source = ASSETS / 'zidane.jpg'
 
     # Predict a segment based on a point prompt
     model.predict(source, points=[900, 370], labels=[1])

tests/test_engine.py

@@ -6,14 +6,13 @@ from ultralytics import YOLO
 from ultralytics.cfg import get_cfg
 from ultralytics.engine.exporter import Exporter
 from ultralytics.models.yolo import classify, detect, segment
-from ultralytics.utils import DEFAULT_CFG, ROOT, SETTINGS
+from ultralytics.utils import ASSETS, DEFAULT_CFG, SETTINGS
 
 CFG_DET = 'yolov8n.yaml'
 CFG_SEG = 'yolov8n-seg.yaml'
 CFG_CLS = 'yolov8n-cls.yaml'  # or 'squeezenet1_0'
 CFG = get_cfg(DEFAULT_CFG)
 MODEL = Path(SETTINGS['weights_dir']) / 'yolov8n'
-SOURCE = ROOT / 'assets'
 
 
 def test_func(*args):  # noqa
@@ -25,7 +24,7 @@ def test_export():
     exporter.add_callback('on_export_start', test_func)
     assert test_func in exporter.callbacks['on_export_start'], 'callback test failed'
     f = exporter(model=YOLO(CFG_DET).model)
-    YOLO(f)(SOURCE)  # exported model inference
+    YOLO(f)(ASSETS)  # exported model inference
 
 
 def test_detect():
@@ -49,7 +48,7 @@ def test_detect():
     pred = detect.DetectionPredictor(overrides={'imgsz': [64, 64]})
     pred.add_callback('on_predict_start', test_func)
     assert test_func in pred.callbacks['on_predict_start'], 'callback test failed'
-    result = pred(source=SOURCE, model=f'{MODEL}.pt')
+    result = pred(source=ASSETS, model=f'{MODEL}.pt')
     assert len(result), 'predictor test failed'
 
     overrides['resume'] = trainer.last
@@ -85,7 +84,7 @@ def test_segment():
     pred = segment.SegmentationPredictor(overrides={'imgsz': [64, 64]})
     pred.add_callback('on_predict_start', test_func)
     assert test_func in pred.callbacks['on_predict_start'], 'callback test failed'
-    result = pred(source=SOURCE, model=f'{MODEL}-seg.pt')
+    result = pred(source=ASSETS, model=f'{MODEL}-seg.pt')
     assert len(result), 'predictor test failed'
 
     # Test resume
@@ -122,5 +121,5 @@ def test_classify():
     pred = classify.ClassificationPredictor(overrides={'imgsz': [64, 64]})
     pred.add_callback('on_predict_start', test_func)
     assert test_func in pred.callbacks['on_predict_start'], 'callback test failed'
-    result = pred(source=SOURCE, model=trainer.best)
+    result = pred(source=ASSETS, model=trainer.best)
     assert len(result), 'predictor test failed'

tests/test_python.py

@@ -13,14 +13,14 @@ from torchvision.transforms import ToTensor
 
 from ultralytics import RTDETR, YOLO
 from ultralytics.data.build import load_inference_source
-from ultralytics.utils import DEFAULT_CFG, LINUX, ONLINE, ROOT, SETTINGS
+from ultralytics.utils import ASSETS, DEFAULT_CFG, LINUX, ONLINE, ROOT, SETTINGS
 from ultralytics.utils.downloads import download
 from ultralytics.utils.torch_utils import TORCH_1_9
 
 WEIGHTS_DIR = Path(SETTINGS['weights_dir'])
 MODEL = WEIGHTS_DIR / 'path with spaces' / 'yolov8n.pt'  # test spaces in path
 CFG = 'yolov8n.yaml'
-SOURCE = ROOT / 'assets/bus.jpg'
+SOURCE = ASSETS / 'bus.jpg'
 TMP = (ROOT / '../tests/tmp').resolve()  # temp directory for test files
 
 
@@ -29,9 +29,14 @@ def test_model_forward():
     model(SOURCE, imgsz=32, augment=True)
 
 
-def test_model_info():
+def test_model_methods():
     model = YOLO(MODEL)
-    model.info(verbose=True)
+    model.info(verbose=True, detailed=True)
+    model = model.reset_weights()
+    model = model.load(MODEL)
+    model.to('cpu')
+    _ = model.names
+    _ = model.device
 
 
 def test_model_fuse():
@@ -41,7 +46,7 @@ def test_model_fuse():
 
 def test_predict_dir():
     model = YOLO(MODEL)
-    model(source=ROOT / 'assets', imgsz=32)
+    model(source=ASSETS, imgsz=32)
 
 
 def test_predict_img():
@@ -102,11 +107,23 @@ def test_predict_grey_and_4ch():
 def test_track_stream():
     # Test YouTube streaming inference (short 10 frame video) with non-default ByteTrack tracker
     # imgsz=160 required for tracking for higher confidence and better matches
+    import yaml
+
     model = YOLO(MODEL)
     model.predict('https://youtu.be/G17sBkb38XQ', imgsz=96)
     model.track('https://ultralytics.com/assets/decelera_portrait_min.mov', imgsz=160, tracker='bytetrack.yaml')
     model.track('https://ultralytics.com/assets/decelera_portrait_min.mov', imgsz=160, tracker='botsort.yaml')
 
+    # Test Global Motion Compensation (GMC) methods
+    for gmc in 'orb', 'sift', 'ecc':
+        with open(ROOT / 'cfg/trackers/botsort.yaml') as f:
+            data = yaml.safe_load(f)
+        tracker = TMP / f'botsort-{gmc}.yaml'
+        data['gmc_method'] = gmc
+        with open(tracker, 'w') as f:
+            yaml.safe_dump(data, f)
+        model.track('https://ultralytics.com/assets/decelera_portrait_min.mov', imgsz=160, tracker=tracker)
+
 
 def test_val():
     model = YOLO(MODEL)
@@ -133,7 +150,7 @@ def test_export_torchscript():
 
 def test_export_onnx():
     model = YOLO(MODEL)
-    f = model.export(format='onnx')
+    f = model.export(format='onnx', dynamic=True)
     YOLO(f)(SOURCE)  # exported model inference
 
 
@@ -173,6 +190,12 @@ def test_export_paddle(enabled=False):
         model.export(format='paddle')
 
 
+def test_export_ncnn(enabled=False):
+    model = YOLO(MODEL)
+    f = model.export(format='ncnn')
+    YOLO(f)(SOURCE)  # exported model inference
+
+
 def test_all_model_yamls():
     for m in (ROOT / 'cfg' / 'models').rglob('*.yaml'):
         if 'rtdetr' in m.name:
@@ -251,12 +274,13 @@ def test_data_utils():
 @pytest.mark.skipif(not ONLINE, reason='environment is offline')
 def test_data_converter():
     # Test dataset converters
-    from ultralytics.data.converter import convert_coco
+    from ultralytics.data.converter import coco80_to_coco91_class, convert_coco
 
     file = 'instances_val2017.json'
     download(f'https://github.com/ultralytics/yolov5/releases/download/v1.0/{file}')
     shutil.move(file, TMP)
     convert_coco(labels_dir=TMP, use_segments=True, use_keypoints=False, cls91to80=True)
+    coco80_to_coco91_class()
 
 
 def test_events():
@@ -270,9 +294,64 @@ def test_events():
     events(cfg)
 
 
+def test_utils_init():
+    from ultralytics.utils import (get_git_branch, get_git_origin_url, get_ubuntu_version, is_github_actions_ci,
+                                   is_ubuntu)
+
+    is_ubuntu()
+    get_ubuntu_version()
+    is_github_actions_ci()
+    get_git_origin_url()
+    get_git_branch()
+
+
 def test_utils_checks():
-    from ultralytics.utils.checks import check_yolov5u_filename, git_describe
+    from ultralytics.utils.checks import check_requirements, check_yolov5u_filename, git_describe
 
-    check_yolov5u_filename('yolov5.pt')
+    check_yolov5u_filename('yolov5n.pt')
     # check_imshow(warn=True)
     git_describe(ROOT)
+    check_requirements()  # check requirements.txt
+
+
+def test_utils_benchmarks():
+    from ultralytics.utils.benchmarks import ProfileModels
+
+    ProfileModels(['yolov8n.yaml'], imgsz=32, min_time=1, num_timed_runs=3, num_warmup_runs=1).profile()
+
+
+def test_utils_torchutils():
+    from ultralytics.nn.modules.conv import Conv
+    from ultralytics.utils.torch_utils import get_flops_with_torch_profiler, profile, time_sync
+
+    x = torch.randn(1, 64, 20, 20)
+    m = Conv(64, 64, k=1, s=2)
+
+    profile(x, [m], n=3)
+    get_flops_with_torch_profiler(m)
+    time_sync()
+
+
+def test_utils_downloads():
+    from ultralytics.utils.downloads import get_google_drive_file_info
+
+    get_google_drive_file_info('https://drive.google.com/file/d/1cqT-cJgANNrhIHCrEufUYhQ4RqiWG_lJ/view?usp=drive_link')
+
+
+def test_utils_ops():
+    from ultralytics.utils.ops import make_divisible
+
+    make_divisible(17, 8)
+
+
+def test_utils_files():
+    from ultralytics.utils.files import file_age, file_date, get_latest_run, spaces_in_path
+
+    file_age(SOURCE)
+    file_date(SOURCE)
+    get_latest_run(ROOT / 'runs')
+
+    path = TMP / 'path/with spaces'
+    path.mkdir(parents=True, exist_ok=True)
+    with spaces_in_path(path) as new_path:
+        print(new_path)

ultralytics/cfg/__init__.py

@@ -9,7 +9,7 @@ from pathlib import Path
 from types import SimpleNamespace
 from typing import Dict, List, Union
 
-from ultralytics.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_PATH, LOGGER, ROOT, SETTINGS, SETTINGS_YAML,
+from ultralytics.utils import (ASSETS, DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_PATH, LOGGER, SETTINGS, SETTINGS_YAML,
                                IterableSimpleNamespace, __version__, checks, colorstr, deprecation_warn, yaml_load,
                                yaml_print)
 
@@ -415,8 +415,7 @@ def entrypoint(debug=''):
 
     # Mode
     if mode in ('predict', 'track') and 'source' not in overrides:
-        overrides['source'] = DEFAULT_CFG.source or ROOT / 'assets' if (ROOT / 'assets').exists() \
+        overrides['source'] = DEFAULT_CFG.source or ASSETS
-            else 'https://ultralytics.com/images/bus.jpg'
         LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using default 'source={overrides['source']}'.")
     elif mode in ('train', 'val'):
         if 'data' not in overrides:

ultralytics/cfg/trackers/botsort.yaml

@@ -11,7 +11,7 @@ match_thresh: 0.8  # threshold for matching tracks
 # mot20: False  # for tracker evaluation(not used for now)
 
 # BoT-SORT settings
-cmc_method: sparseOptFlow  # method of global motion compensation
+gmc_method: sparseOptFlow  # method of global motion compensation
 # ReID model related thresh (not supported yet)
 proximity_thresh: 0.5
 appearance_thresh: 0.25

ultralytics/data/converter.py

@@ -1,6 +1,7 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
 import json
+import shutil
 from collections import defaultdict
 from pathlib import Path
 
@@ -9,7 +10,6 @@ import numpy as np
 from tqdm import tqdm
 
 from ultralytics.utils.checks import check_requirements
-from ultralytics.utils.files import make_dirs
 
 
 def coco91_to_coco80_class():
@@ -27,6 +27,27 @@ def coco91_to_coco80_class():
         None, 73, 74, 75, 76, 77, 78, 79, None]
 
 
+def coco80_to_coco91_class():  #
+    """
+    Converts 80-index (val2014) to 91-index (paper).
+    For details see https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/.
+
+    Example:
+        ```python
+        import numpy as np
+
+        a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
+        b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
+        x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
+        x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
+        ```
+    """
+    return [
+        1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
+        35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+        64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
+
+
 def convert_coco(labels_dir='../coco/annotations/', use_segments=False, use_keypoints=False, cls91to80=True):
     """Converts COCO dataset annotations to a format suitable for training YOLOv5 models.
 
@@ -47,7 +68,14 @@ def convert_coco(labels_dir='../coco/annotations/', use_segments=False, use_keyp
         Generates output files in the specified output directory.
     """
 
-    save_dir = make_dirs('yolo_labels')  # output directory
+    # Create dataset directory
+    save_dir = Path('yolo_labels')
+    if save_dir.exists():
+        shutil.rmtree(save_dir)  # delete dir
+    for p in save_dir / 'labels', save_dir / 'images':
+        p.mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Convert classes
     coco80 = coco91_to_coco80_class()
 
     # Import json

ultralytics/data/loaders.py

@@ -16,7 +16,7 @@ import torch
 from PIL import Image
 
 from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS
-from ultralytics.utils import LOGGER, ROOT, is_colab, is_kaggle, ops
+from ultralytics.utils import ASSETS, LOGGER, is_colab, is_kaggle, ops
 from ultralytics.utils.checks import check_requirements
 
 
@@ -403,7 +403,7 @@ def get_best_youtube_url(url, use_pafy=False):
 
 
 if __name__ == '__main__':
-    img = cv2.imread(str(ROOT / 'assets/bus.jpg'))
+    img = cv2.imread(str(ASSETS / 'bus.jpg'))
     dataset = LoadPilAndNumpy(im0=img)
     for d in dataset:
         print(d[0])

ultralytics/engine/model.py

@@ -9,8 +9,8 @@ from ultralytics.cfg import get_cfg
 from ultralytics.engine.exporter import Exporter
 from ultralytics.hub.utils import HUB_WEB_ROOT
 from ultralytics.nn.tasks import attempt_load_one_weight, guess_model_task, nn, yaml_model_load
-from ultralytics.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, ROOT, callbacks, emojis,
+from ultralytics.utils import (ASSETS, DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, callbacks, emojis,
-                               is_git_dir, yaml_load)
+                               yaml_load)
 from ultralytics.utils.checks import check_file, check_imgsz, check_pip_update_available, check_yaml
 from ultralytics.utils.downloads import GITHUB_ASSET_STEMS
 from ultralytics.utils.torch_utils import smart_inference_mode
@@ -218,7 +218,7 @@ class Model:
             (List[ultralytics.engine.results.Results]): The prediction results.
         """
         if source is None:
-            source = ROOT / 'assets' if is_git_dir() else 'https://ultralytics.com/images/bus.jpg'
+            source = ASSETS
             LOGGER.warning(f"WARNING ⚠️ 'source' is missing. Using 'source={source}'.")
         is_cli = (sys.argv[0].endswith('yolo') or sys.argv[0].endswith('ultralytics')) and any(
             x in sys.argv for x in ('predict', 'track', 'mode=predict', 'mode=track'))
@@ -390,6 +390,7 @@ class Model:
         """
         self._check_is_pytorch_model()
         self.model.to(device)
+        return self
 
     def tune(self, *args, **kwargs):
         """

ultralytics/engine/predictor.py

@@ -47,7 +47,7 @@ STREAM_WARNING = """
     WARNING ⚠️ stream/video/webcam/dir predict source will accumulate results in RAM unless `stream=True` is passed,
     causing potential out-of-memory errors for large sources or long-running streams/videos.
 
-    Usage:
+    Example:
         results = model(source=..., stream=True)  # generator of Results objects
         for r in results:
             boxes = r.boxes  # Boxes object for bbox outputs

ultralytics/models/rtdetr/train.py

@@ -59,7 +59,7 @@ class RTDETRTrainer(DetectionTrainer):
 def train(cfg=DEFAULT_CFG, use_python=False):
     """Train and optimize RTDETR model given training data and device."""
     model = 'rtdetr-l.yaml'
-    data = cfg.data or 'coco128.yaml'  # or yolo.ClassificationDataset("mnist")
+    data = cfg.data or 'coco8.yaml'  # or yolo.ClassificationDataset("mnist")
     device = cfg.device if cfg.device is not None else ''
 
     # NOTE: F.grid_sample which is in rt-detr does not support deterministic=True

ultralytics/models/yolo/classify/predict.py

@@ -4,7 +4,7 @@ import torch
 
 from ultralytics.engine.predictor import BasePredictor
 from ultralytics.engine.results import Results
-from ultralytics.utils import DEFAULT_CFG, ROOT
+from ultralytics.utils import ASSETS, DEFAULT_CFG
 
 
 class ClassificationPredictor(BasePredictor):
@@ -35,8 +35,7 @@ class ClassificationPredictor(BasePredictor):
 def predict(cfg=DEFAULT_CFG, use_python=False):
     """Run YOLO model predictions on input images/videos."""
     model = cfg.model or 'yolov8n-cls.pt'  # or "resnet18"
-    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
+    source = cfg.source or ASSETS
-        else 'https://ultralytics.com/images/bus.jpg'
 
     args = dict(model=model, source=source)
     if use_python:

ultralytics/models/yolo/detect/predict.py

@@ -4,7 +4,7 @@ import torch
 
 from ultralytics.engine.predictor import BasePredictor
 from ultralytics.engine.results import Results
-from ultralytics.utils import DEFAULT_CFG, ROOT, ops
+from ultralytics.utils import ASSETS, DEFAULT_CFG, ops
 
 
 class DetectionPredictor(BasePredictor):
@@ -32,8 +32,7 @@ class DetectionPredictor(BasePredictor):
 def predict(cfg=DEFAULT_CFG, use_python=False):
     """Runs YOLO model inference on input image(s)."""
     model = cfg.model or 'yolov8n.pt'
-    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
+    source = cfg.source or ASSETS
-        else 'https://ultralytics.com/images/bus.jpg'
 
     args = dict(model=model, source=source)
     if use_python:

ultralytics/models/yolo/detect/train.py

@@ -107,7 +107,7 @@ class DetectionTrainer(BaseTrainer):
 def train(cfg=DEFAULT_CFG, use_python=False):
     """Train and optimize YOLO model given training data and device."""
     model = cfg.model or 'yolov8n.pt'
-    data = cfg.data or 'coco128.yaml'  # or yolo.ClassificationDataset("mnist")
+    data = cfg.data or 'coco8.yaml'  # or yolo.ClassificationDataset("mnist")
     device = cfg.device if cfg.device is not None else ''
 
     args = dict(model=model, data=data, device=device)

ultralytics/models/yolo/detect/val.py

@@ -6,7 +6,7 @@ from pathlib import Path
 import numpy as np
 import torch
 
-from ultralytics.data import build_dataloader, build_yolo_dataset
+from ultralytics.data import build_dataloader, build_yolo_dataset, converter
 from ultralytics.engine.validator import BaseValidator
 from ultralytics.utils import DEFAULT_CFG, LOGGER, ops
 from ultralytics.utils.checks import check_requirements
@@ -50,7 +50,7 @@ class DetectionValidator(BaseValidator):
         """Initialize evaluation metrics for YOLO."""
         val = self.data.get(self.args.split, '')  # validation path
         self.is_coco = isinstance(val, str) and 'coco' in val and val.endswith(f'{os.sep}val2017.txt')  # is COCO
-        self.class_map = ops.coco80_to_coco91_class() if self.is_coco else list(range(1000))
+        self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1000))
         self.args.save_json |= self.is_coco and not self.training  # run on final val if training COCO
         self.names = model.names
         self.nc = len(model.names)
@@ -259,7 +259,7 @@ class DetectionValidator(BaseValidator):
 def val(cfg=DEFAULT_CFG, use_python=False):
     """Validate trained YOLO model on validation dataset."""
     model = cfg.model or 'yolov8n.pt'
-    data = cfg.data or 'coco128.yaml'
+    data = cfg.data or 'coco8.yaml'
 
     args = dict(model=model, data=data)
     if use_python:

ultralytics/models/yolo/pose/predict.py

@@ -2,7 +2,7 @@
 
 from ultralytics.engine.results import Results
 from ultralytics.models.yolo.detect.predict import DetectionPredictor
-from ultralytics.utils import DEFAULT_CFG, LOGGER, ROOT, ops
+from ultralytics.utils import ASSETS, DEFAULT_CFG, LOGGER, ops
 
 
 class PosePredictor(DetectionPredictor):
@@ -45,8 +45,7 @@ class PosePredictor(DetectionPredictor):
 def predict(cfg=DEFAULT_CFG, use_python=False):
     """Runs YOLO to predict objects in an image or video."""
     model = cfg.model or 'yolov8n-pose.pt'
-    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
+    source = cfg.source or ASSETS
-        else 'https://ultralytics.com/images/bus.jpg'
 
     args = dict(model=model, source=source)
     if use_python:

ultralytics/models/yolo/segment/predict.py

@@ -4,7 +4,7 @@ import torch
 
 from ultralytics.engine.results import Results
 from ultralytics.models.yolo.detect.predict import DetectionPredictor
-from ultralytics.utils import DEFAULT_CFG, ROOT, ops
+from ultralytics.utils import ASSETS, DEFAULT_CFG, ops
 
 
 class SegmentationPredictor(DetectionPredictor):
@@ -47,8 +47,7 @@ class SegmentationPredictor(DetectionPredictor):
 def predict(cfg=DEFAULT_CFG, use_python=False):
     """Runs YOLO object detection on an image or video source."""
     model = cfg.model or 'yolov8n-seg.pt'
-    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
+    source = cfg.source or ASSETS
-        else 'https://ultralytics.com/images/bus.jpg'
 
     args = dict(model=model, source=source)
     if use_python:

ultralytics/models/yolo/segment/train.py

@@ -49,7 +49,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
 def train(cfg=DEFAULT_CFG, use_python=False):
     """Train a YOLO segmentation model based on passed arguments."""
     model = cfg.model or 'yolov8n-seg.pt'
-    data = cfg.data or 'coco128-seg.yaml'  # or yolo.ClassificationDataset("mnist")
+    data = cfg.data or 'coco8-seg.yaml'
     device = cfg.device if cfg.device is not None else ''
 
     args = dict(model=model, data=data, device=device)

ultralytics/models/yolo/segment/val.py

@@ -236,7 +236,7 @@ class SegmentationValidator(DetectionValidator):
 def val(cfg=DEFAULT_CFG, use_python=False):
     """Validate trained YOLO model on validation data."""
     model = cfg.model or 'yolov8n-seg.pt'
-    data = cfg.data or 'coco128-seg.yaml'
+    data = cfg.data or 'coco8-seg.yaml'
 
     args = dict(model=model, data=data)
     if use_python:

ultralytics/nn/tasks.py

@@ -303,13 +303,6 @@ class SegmentationModel(DetectionModel):
     def init_criterion(self):
         return v8SegmentationLoss(self)
 
-    def _predict_augment(self, x):
-        """Perform augmentations on input image x and return augmented inference."""
-        LOGGER.warning(
-            f'WARNING ⚠️ {self.__class__.__name__} has not supported augment inference yet! Now using single-scale inference instead.'
-        )
-        return self._predict_once(x)
-
 
 class PoseModel(DetectionModel):
     """YOLOv8 pose model."""
@@ -326,13 +319,6 @@ class PoseModel(DetectionModel):
     def init_criterion(self):
         return v8PoseLoss(self)
 
-    def _predict_augment(self, x):
-        """Perform augmentations on input image x and return augmented inference."""
-        LOGGER.warning(
-            f'WARNING ⚠️ {self.__class__.__name__} has not supported augment inference yet! Now using single-scale inference instead.'
-        )
-        return self._predict_once(x)
-
 
 class ClassificationModel(BaseModel):
     """YOLOv8 classification model."""

ultralytics/trackers/bot_sort.py

@@ -110,8 +110,7 @@ class BOTSORT(BYTETracker):
         if args.with_reid:
             # Haven't supported BoT-SORT(reid) yet
             self.encoder = None
-        # self.gmc = GMC(method=args.cmc_method, verbose=[args.name, args.ablation])
+        self.gmc = GMC(method=args.gmc_method)
-        self.gmc = GMC(method=args.cmc_method)
 
     def get_kalmanfilter(self):
         """Returns an instance of KalmanFilterXYWH for object tracking."""

ultralytics/trackers/utils/gmc.py

@@ -10,7 +10,7 @@ from ultralytics.utils import LOGGER
 
 class GMC:
 
-    def __init__(self, method='sparseOptFlow', downscale=2, verbose=None):
+    def __init__(self, method='sparseOptFlow', downscale=2):
         """Initialize a video tracker with specified parameters."""
         super().__init__()
 
@@ -40,28 +40,11 @@ class GMC:
                                        blockSize=3,
                                        useHarrisDetector=False,
                                        k=0.04)
-            # self.gmc_file = open('GMC_results.txt', 'w')
+
-
+        elif self.method in ['none', 'None', None]:
-        elif self.method in ['file', 'files']:
+            self.method = None
-            seqName = verbose[0]
-            ablation = verbose[1]
-            if ablation:
-                filePath = r'tracker/GMC_files/MOT17_ablation'
-            else:
-                filePath = r'tracker/GMC_files/MOTChallenge'
-
-            if '-FRCNN' in seqName:
-                seqName = seqName[:-6]
-            elif '-DPM' in seqName or '-SDP' in seqName:
-                seqName = seqName[:-4]
-            self.gmcFile = open(f'{filePath}/GMC-{seqName}.txt')
-
-            if self.gmcFile is None:
-                raise ValueError(f'Error: Unable to open GMC file in directory:{filePath}')
-        elif self.method in ['none', 'None']:
-            self.method = 'none'
         else:
-            raise ValueError(f'Error: Unknown CMC method:{method}')
+            raise ValueError(f'Error: Unknown GMC method:{method}')
 
         self.prevFrame = None
         self.prevKeyPoints = None
@@ -77,10 +60,6 @@ class GMC:
             return self.applyEcc(raw_frame, detections)
         elif self.method == 'sparseOptFlow':
             return self.applySparseOptFlow(raw_frame, detections)
-        elif self.method == 'file':
-            return self.applyFile(raw_frame, detections)
-        elif self.method == 'none':
-            return np.eye(2, 3)
         else:
             return np.eye(2, 3)
 
@@ -244,7 +223,6 @@ class GMC:
 
     def applySparseOptFlow(self, raw_frame, detections=None):
         """Initialize."""
-        # t0 = time.time()
         height, width, _ = raw_frame.shape
         frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
         H = np.eye(2, 3)
@@ -298,22 +276,4 @@ class GMC:
         self.prevFrame = frame.copy()
         self.prevKeyPoints = copy.copy(keypoints)
 
-        # gmc_line = str(1000 * (time.time() - t0)) + "\t" + str(H[0, 0]) + "\t" + str(H[0, 1]) + "\t" + str(
-        #     H[0, 2]) + "\t" + str(H[1, 0]) + "\t" + str(H[1, 1]) + "\t" + str(H[1, 2]) + "\n"
-        # self.gmc_file.write(gmc_line)
-
-        return H
-
-    def applyFile(self, raw_frame, detections=None):
-        """Return the homography matrix based on the GCPs in the next line of the input GMC file."""
-        line = self.gmcFile.readline()
-        tokens = line.split('\t')
-        H = np.eye(2, 3, dtype=np.float_)
-        H[0, 0] = float(tokens[1])
-        H[0, 1] = float(tokens[2])
-        H[0, 2] = float(tokens[3])
-        H[1, 0] = float(tokens[4])
-        H[1, 1] = float(tokens[5])
-        H[1, 2] = float(tokens[6])
-
         return H

ultralytics/utils/__init__.py

@@ -30,6 +30,7 @@ LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable
 # Other Constants
 FILE = Path(__file__).resolve()
 ROOT = FILE.parents[1]  # YOLO
+ASSETS = ROOT / 'assets'  # default images
 DEFAULT_CFG_PATH = ROOT / 'cfg/default.yaml'
 NUM_THREADS = min(8, max(1, os.cpu_count() - 1))  # number of YOLOv5 multiprocessing threads
 AUTOINSTALL = str(os.getenv('YOLO_AUTOINSTALL', True)).lower() == 'true'  # global auto-install mode
@@ -260,11 +261,15 @@ class ThreadingLocked:
     Attributes:
         lock (threading.Lock): A lock object used to manage access to the decorated function.
 
-    Usage:
+    Example:
+        ```python
+        from ultralytics.utils import ThreadingLocked
+
         @ThreadingLocked()
         def my_function():
             # Your code here
             pass
+        ```
     """
 
     def __init__(self):
@@ -518,7 +523,6 @@ def get_git_dir():
     for d in Path(__file__).parents:
         if (d / '.git').is_dir():
             return d
-    return None  # no .git dir found
 
 
 def get_git_origin_url():
@@ -526,13 +530,12 @@ def get_git_origin_url():
     Retrieves the origin URL of a git repository.
 
     Returns:
-        (str | None): The origin URL of the git repository.
+        (str | None): The origin URL of the git repository or None if not git directory.
     """
     if is_git_dir():
         with contextlib.suppress(subprocess.CalledProcessError):
             origin = subprocess.check_output(['git', 'config', '--get', 'remote.origin.url'])
             return origin.decode().strip()
-    return None  # if not git dir or on error
 
 
 def get_git_branch():
@@ -540,13 +543,12 @@ def get_git_branch():
     Returns the current git branch name. If not in a git repository, returns None.
 
     Returns:
-        (str | None): The current git branch name.
+        (str | None): The current git branch name or None if not a git directory.
     """
     if is_git_dir():
         with contextlib.suppress(subprocess.CalledProcessError):
             origin = subprocess.check_output(['git', 'rev-parse', '--abbrev-ref', 'HEAD'])
             return origin.decode().strip()
-    return None  # if not git dir or on error
 
 
 def get_default_args(func):
@@ -572,7 +574,6 @@ def get_ubuntu_version():
     with contextlib.suppress(FileNotFoundError, AttributeError):
         with open('/etc/os-release') as f:
             return re.search(r'VERSION_ID="(\d+\.\d+)"', f.read())[1]
-    return None
 
 
 def get_user_config_dir(sub_dir='Ultralytics'):

ultralytics/utils/benchmarks.py

@@ -37,9 +37,8 @@ from tqdm import tqdm
 from ultralytics import YOLO
 from ultralytics.cfg import TASK2DATA, TASK2METRIC
 from ultralytics.engine.exporter import export_formats
-from ultralytics.utils import LINUX, LOGGER, MACOS, ROOT, SETTINGS
+from ultralytics.utils import ASSETS, LINUX, LOGGER, MACOS, SETTINGS
 from ultralytics.utils.checks import check_requirements, check_yolo
-from ultralytics.utils.downloads import download
 from ultralytics.utils.files import file_size
 from ultralytics.utils.torch_utils import select_device
 
@@ -68,6 +67,13 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
     Returns:
         df (pandas.DataFrame): A pandas DataFrame with benchmark results for each format, including file size,
             metric, and inference time.
+
+    Example:
+        ```python
+        from ultralytics.utils.benchmarks import benchmark
+
+        benchmark(model='yolov8n.pt', imgsz=640)
+        ```
     """
 
     import pandas as pd
@@ -106,9 +112,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
             assert model.task != 'pose' or i != 7, 'GraphDef Pose inference is not supported'
             assert i not in (9, 10), 'inference not supported'  # Edge TPU and TF.js are unsupported
             assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13'  # CoreML
-            if not (ROOT / 'assets/bus.jpg').exists():
+            export.predict(ASSETS / 'bus.jpg', imgsz=imgsz, device=device, half=half)
-                download(url='https://ultralytics.com/images/bus.jpg', dir=ROOT / 'assets')
-            export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half)
 
             # Validate
             data = data or TASK2DATA[model.task]  # task to dataset, i.e. coco8.yaml for task=detect
@@ -163,6 +167,13 @@ class ProfileModels:
 
     Methods:
         profile(): Profiles the models and prints the result.
+
+    Example:
+        ```python
+        from ultralytics.utils.benchmarks import ProfileModels
+
+        ProfileModels(['yolov8n.yaml', 'yolov8s.yaml'], imgsz=640).profile()
+        ```
     """
 
     def __init__(self,
@@ -353,11 +364,3 @@ class ProfileModels:
         print(separator)
         for row in table_rows:
             print(row)
-
-
-if __name__ == '__main__':
-    # Benchmark all export formats
-    benchmark()
-
-    # Profiling models on ONNX and TensorRT
-    ProfileModels(['yolov8n.yaml', 'yolov8s.yaml'])

ultralytics/utils/checks.py

@@ -20,7 +20,7 @@ import requests
 import torch
 from matplotlib import font_manager
 
-from ultralytics.utils import (AUTOINSTALL, LOGGER, ONLINE, ROOT, USER_CONFIG_DIR, ThreadingLocked, TryExcept,
+from ultralytics.utils import (ASSETS, AUTOINSTALL, LOGGER, ONLINE, ROOT, USER_CONFIG_DIR, ThreadingLocked, TryExcept,
                                clean_url, colorstr, downloads, emojis, is_colab, is_docker, is_jupyter, is_kaggle,
                                is_online, is_pip_package, url2file)
 
@@ -460,8 +460,7 @@ def check_amp(model):
         del m
         return a.shape == b.shape and torch.allclose(a, b.float(), atol=0.5)  # close to 0.5 absolute tolerance
 
-    f = ROOT / 'assets/bus.jpg'  # image to check
+    im = ASSETS / 'bus.jpg'  # image to check
-    im = f if f.exists() else 'https://ultralytics.com/images/bus.jpg' if ONLINE else np.ones((640, 640, 3))
     prefix = colorstr('AMP: ')
     LOGGER.info(f'{prefix}running Automatic Mixed Precision (AMP) checks with YOLOv8n...')
     warning_msg = "Setting 'amp=True'. If you experience zero-mAP or NaN losses you can disable AMP with amp=False."
@@ -484,11 +483,9 @@ def check_amp(model):
 
 def git_describe(path=ROOT):  # path must be a directory
     """Return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe."""
-    try:
+    with contextlib.suppress(Exception):
-        assert (Path(path) / '.git').is_dir()
         return subprocess.check_output(f'git -C {path} describe --tags --long --always', shell=True).decode()[:-1]
-    except AssertionError:
+    return ''
-        return ''
 
 
 def print_args(args: Optional[dict] = None, show_file=True, show_func=False):

ultralytics/utils/files.py

@@ -42,6 +42,8 @@ def spaces_in_path(path):
 
     Example:
         ```python
+        with ultralytics.utils.files import spaces_in_path
+
         with spaces_in_path('/path/with spaces') as new_path:
             # your code here
         ```
@@ -143,13 +145,3 @@ def get_latest_run(search_dir='.'):
     """Return path to most recent 'last.pt' in /runs (i.e. to --resume from)."""
     last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
     return max(last_list, key=os.path.getctime) if last_list else ''
-
-
-def make_dirs(dir='new_dir/'):
-    """Create directories."""
-    dir = Path(dir)
-    if dir.exists():
-        shutil.rmtree(dir)  # delete dir
-    for p in dir, dir / 'labels', dir / 'images':
-        p.mkdir(parents=True, exist_ok=True)  # make dir
-    return dir

ultralytics/utils/ops.py

@@ -55,27 +55,6 @@ class Profile(contextlib.ContextDecorator):
         return time.time()
 
 
-def coco80_to_coco91_class():  #
-    """
-    Converts 80-index (val2014) to 91-index (paper).
-    For details see https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/.
-
-    Example:
-        ```python
-        import numpy as np
-
-        a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
-        b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
-        x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
-        x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
-        ```
-    """
-    return [
-        1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
-        35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
-        64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
-
-
 def segment2box(segment, width=640, height=640):
     """
     Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)

ultralytics/utils/torch_utils.py

@@ -239,16 +239,18 @@ def get_flops(model, imgsz=640):
 
 def get_flops_with_torch_profiler(model, imgsz=640):
     """Compute model FLOPs (thop alternative)."""
-    model = de_parallel(model)
+    if TORCH_2_0:
-    p = next(model.parameters())
+        model = de_parallel(model)
-    stride = (max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32) * 2  # max stride
+        p = next(model.parameters())
-    im = torch.zeros((1, p.shape[1], stride, stride), device=p.device)  # input image in BCHW format
+        stride = (max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32) * 2  # max stride
-    with torch.profiler.profile(with_flops=True) as prof:
+        im = torch.zeros((1, p.shape[1], stride, stride), device=p.device)  # input image in BCHW format
-        model(im)
+        with torch.profiler.profile(with_flops=True) as prof:
-    flops = sum(x.flops for x in prof.key_averages()) / 1E9
+            model(im)
-    imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz]  # expand if int/float
+        flops = sum(x.flops for x in prof.key_averages()) / 1E9
-    flops = flops * imgsz[0] / stride * imgsz[1] / stride  # 640x640 GFLOPs
+        imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz]  # expand if int/float
-    return flops
+        flops = flops * imgsz[0] / stride * imgsz[1] / stride  # 640x640 GFLOPs
+        return flops
+    return 0
 
 
 def initialize_weights(model):
@@ -384,11 +386,14 @@ def strip_optimizer(f: Union[str, Path] = 'best.pt', s: str = '') -> None:
     Returns:
         None
 
-    Usage:
+    Example:
+        ```python
         from pathlib import Path
         from ultralytics.utils.torch_utils import strip_optimizer
-        for f in Path('/Users/glennjocher/Downloads/weights').rglob('*.pt'):
+
+        for f in Path('path/to/weights').rglob('*.pt'):
             strip_optimizer(f)
+        ```
     """
     # Use dill (if exists) to serialize the lambda functions where pickle does not do this
     try:
@@ -421,13 +426,17 @@ def strip_optimizer(f: Union[str, Path] = 'best.pt', s: str = '') -> None:
 
 def profile(input, ops, n=10, device=None):
     """
-    YOLOv8 speed/memory/FLOPs profiler
+    Ultralytics speed, memory and FLOPs profiler.
+
+    Example:
+        ```python
+        from ultralytics.utils.torch_utils import profile
 
-    Usage:
         input = torch.randn(16, 3, 640, 640)
         m1 = lambda x: x * torch.sigmoid(x)
         m2 = nn.SiLU()
         profile(input, [m1, m2], n=100)  # profile over 100 iterations
+        ```
     """
     results = []
     if not isinstance(device, torch.device):