Merge branch 'main' into LeYOLO-Docs-Page

.github/workflows/ci.yaml

@@ -156,7 +156,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-14]
+        os: [ubuntu-latest, macos-14, windows-latest]
         python-version: ["3.11"]
         torch: [latest]
         include:

.github/workflows/docs.yml

@@ -46,7 +46,7 @@ jobs:
         run: pip install ruff black tqdm mkdocs-material "mkdocstrings[python]" mkdocs-jupyter mkdocs-redirects mkdocs-ultralytics-plugin mkdocs-macros-plugin
       - name: Ruff fixes
         continue-on-error: true
-        run: ruff check --fix --fix-unsafe --select D --ignore=D100,D104,D203,D205,D212,D213,D401,D406,D407,D413 .
+        run: ruff check --fix --unsafe-fixes --select D --ignore=D100,D104,D203,D205,D212,D213,D401,D406,D407,D413 .
       - name: Update Docs Reference Section and Push Changes
         if: github.event_name == 'pull_request_target'
         run: |

.github/workflows/publish.yml

@@ -34,7 +34,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip wheel
-          pip install openai requests build twine toml
+          pip install requests build twine toml
       - name: Check PyPI version
         shell: python
         run: |
@@ -79,8 +79,8 @@ jobs:
               publish = True  # First release
 
           os.system(f'echo "increment={publish}" >> $GITHUB_OUTPUT')
-          os.system(f'echo "version={local_version}" >> $GITHUB_OUTPUT')
-          os.system(f'echo "previous_version={online_version or "N/A"}" >> $GITHUB_OUTPUT')
+          os.system(f'echo "current_tag=v{local_version}" >> $GITHUB_OUTPUT')
+          os.system(f'echo "previous_tag=v{online_version}" >> $GITHUB_OUTPUT')
 
           if publish:
               print('Ready to publish new version to PyPI ✅.')
@@ -88,81 +88,18 @@ jobs:
       - name: Publish new tag
         if: (github.event_name == 'push' || github.event.inputs.pypi == 'true')  && steps.check_pypi.outputs.increment == 'True'
         run: |
-          git tag -a "v${{ steps.check_pypi.outputs.version }}" -m "$(git log -1 --pretty=%B)"  # i.e. "v0.1.2 commit message"
-          git push origin "v${{ steps.check_pypi.outputs.version }}"
+          git tag -a "${{ steps.check_pypi.outputs.current_tag }}" -m "$(git log -1 --pretty=%B)"  # i.e. "v0.1.2 commit message"
+          git push origin "${{ steps.check_pypi.outputs.current_tag }}"
       - name: Publish new release
         if: (github.event_name == 'push' || github.event.inputs.pypi == 'true')  && steps.check_pypi.outputs.increment == 'True'
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN || secrets.GITHUB_TOKEN }}
-          CURRENT_TAG: ${{ steps.check_pypi.outputs.version }}
-          PREVIOUS_TAG: ${{ steps.check_pypi.outputs.previous_version }}
-        shell: python
+          CURRENT_TAG: ${{ steps.check_pypi.outputs.current_tag }}
+          PREVIOUS_TAG: ${{ steps.check_pypi.outputs.previous_tag }}
         run: |
-          import openai
-          import os
-          import requests
-          import json
-          import subprocess
-
-          # Retrieve environment variables
-          OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
-          GITHUB_TOKEN = os.getenv('GITHUB_TOKEN')
-          CURRENT_TAG = os.getenv('CURRENT_TAG')
-          PREVIOUS_TAG = os.getenv('PREVIOUS_TAG')
-
-          # Check for required environment variables
-          if not all([OPENAI_API_KEY, GITHUB_TOKEN, CURRENT_TAG, PREVIOUS_TAG]):
-              raise ValueError("One or more required environment variables are missing.")
-
-          latest_tag = f"v{CURRENT_TAG}"
-          previous_tag = f"v{PREVIOUS_TAG}"
-          repo = os.getenv('GITHUB_REPOSITORY')
-          headers = {"Authorization": f"token {GITHUB_TOKEN}", "Accept": "application/vnd.github.v3.diff"}
-
-          # Get the diff between the tags
-          url = f"https://api.github.com/repos/{repo}/compare/{previous_tag}...{latest_tag}"
-          response = requests.get(url, headers=headers)
-          diff = response.text if response.status_code == 200 else f"Failed to get diff: {response.content}"
-
-          # Get summary
-          messages = [
-              {
-                  "role": "system",
-                  "content": "You are an Ultralytics AI assistant skilled in software development and technical communication. Your task is to summarize GitHub releases in a way that is detailed, accurate, and understandable to both expert developers and non-expert users. Focus on highlighting the key changes and their impact in simple and intuitive terms."
-              },
-              {
-                  "role": "user",
-                  "content": f"Summarize the updates made in the '{latest_tag}' tag, focusing on major changes, their purpose, and potential impact. Keep the summary clear and suitable for a broad audience. Add emojis to enliven the summary. Reply directly with a summary along these example guidelines, though feel free to adjust as appropriate:\n\n"
-                             f"## 🌟 Summary (single-line synopsis)\n"
-                             f"## 📊 Key Changes (bullet points highlighting any major changes)\n"
-                             f"## 🎯 Purpose & Impact (bullet points explaining any benefits and potential impact to users)\n"
-                             f"\n\nHere's the release diff:\n\n{diff[:300000]}",
-              }
-          ]
-          client = openai.OpenAI(api_key=OPENAI_API_KEY)
-          completion = client.chat.completions.create(model="gpt-4o-2024-08-06", messages=messages)
-          summary = completion.choices[0].message.content.strip()
-
-          # Get the latest commit message
-          commit_message = subprocess.run(['git', 'log', '-1', '--pretty=%B'], check=True, text=True, capture_output=True).stdout.split("\n")[0].strip()
-
-          # Prepare release data
-          release = {
-              'tag_name': latest_tag,
-              'name': f"{latest_tag} - {commit_message}",
-              'body': summary,
-              'draft': False,
-              'prerelease': False
-          }
-
-          # Create the release on GitHub
-          release_url = f"https://api.github.com/repos/{repo}/releases"
-          release_response = requests.post(release_url, headers=headers, data=json.dumps(release))
-          if release_response.status_code == 201:
-              print(f'Successfully created release {latest_tag}')
-          else:
-              print(f'Failed to create release {latest_tag}: {release_response.content}')
+          curl -s "https://raw.githubusercontent.com/ultralytics/actions/main/utils/summarize_release.py" | python -
+        shell: bash
       - name: Publish to PyPI
         continue-on-error: true
         if: (github.event_name == 'push' || github.event.inputs.pypi == 'true')  && steps.check_pypi.outputs.increment == 'True'
@@ -193,7 +130,7 @@ jobs:
         uses: slackapi/slack-github-action@v1.26.0
         with:
           payload: |
-            {"text": "<!channel> GitHub Actions success for ${{ github.workflow }} ✅\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* NEW '${{ github.repository }} v${{ steps.check_pypi.outputs.version }}' pip package published 😃\n*Job Status:* ${{ job.status }}\n*Pull Request:* <https://github.com/${{ github.repository }}/pull/${{ env.PR_NUMBER }}> ${{ env.PR_TITLE }}\n"}
+            {"text": "<!channel> GitHub Actions success for ${{ github.workflow }} ✅\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* NEW '${{ github.repository }} ${{ steps.check_pypi.outputs.current_tag }}' pip package published 😃\n*Job Status:* ${{ job.status }}\n*Pull Request:* <https://github.com/${{ github.repository }}/pull/${{ env.PR_NUMBER }}> ${{ env.PR_TITLE }}\n"}
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_YOLO }}
       - name: Notify on Slack (Failure)

docs/build_docs.py

@@ -164,7 +164,7 @@ def update_docs_html():
     # Convert plaintext links to HTML hyperlinks
     files_modified = 0
     for html_file in tqdm(SITE.rglob("*.html"), desc="Converting plaintext links"):
-        with open(html_file, "r", encoding="utf-8") as file:
+        with open(html_file, encoding="utf-8") as file:
             content = file.read()
         updated_content = convert_plaintext_links_to_html(content)
         if updated_content != content:

docs/mkdocs_github_authors.yaml

@@ -1,46 +1,120 @@
-116908874+jk4e@users.noreply.github.com: jk4e
-1185102784@qq.com: Laughing-q
-130829914+IvorZhu331@users.noreply.github.com: IvorZhu331
-135830346+UltralyticsAssistant@users.noreply.github.com: UltralyticsAssistant
-1579093407@qq.com: YOLOv5-Magic
-17216799+ouphi@users.noreply.github.com: ouphi
-17316848+maianumerosky@users.noreply.github.com: maianumerosky
-34196005+fcakyon@users.noreply.github.com: fcakyon
-37276661+capjamesg@users.noreply.github.com: capjamesg
-39910262+ChaoningZhang@users.noreply.github.com: ChaoningZhang
-40165666+berry-ding@users.noreply.github.com: berry-ding
-47978446+sergiuwaxmann@users.noreply.github.com: sergiuwaxmann
-48149018+zhixuwei@users.noreply.github.com: zhixuwei
-49699333+dependabot[bot]@users.noreply.github.com: dependabot
-52826299+Chayanonjackal@users.noreply.github.com: Chayanonjackal
-53246858+hasanghaffari93@users.noreply.github.com: hasanghaffari93
-60036186+mfloto@users.noreply.github.com: mfloto
-61612323+Laughing-q@users.noreply.github.com: Laughing-q
-62214284+Burhan-Q@users.noreply.github.com: Burhan-Q
-68285002+Kayzwer@users.noreply.github.com: Kayzwer
-75611662+tensorturtle@users.noreply.github.com: tensorturtle
-78843978+Skillnoob@users.noreply.github.com: Skillnoob
-79740115+0xSynapse@users.noreply.github.com: 0xSynapse
-Francesco.mttl@gmail.com: ambitious-octopus
-abirami.vina@gmail.com: abirami-vina
-ahmelsamahy@gmail.com: Ahelsamahy
-andrei.kochin@intel.com: andrei-kochin
-ayush.chaurarsia@gmail.com: AyushExel
-chr043416@gmail.com: RizwanMunawar
-glenn.jocher@ultralytics.com: glenn-jocher
-hnliu_2@stu.xidian.edu.cn: null
-jpedrofonseca_94@hotmail.com: null
-k-2feng@hotmail.com: null
-lakshantha@ultralytics.com: lakshanthad
-lakshanthad@yahoo.com: lakshanthad
-muhammadrizwanmunawar123@gmail.com: RizwanMunawar
-not.committed.yet: null
-plashchynski@gmail.com: plashchynski
-priytosh.revolution@live.com: priytosh-tripathi
-rulosanti@gmail.com: null
-shuizhuyuanluo@126.com: null
-sometimesocrazy@gmail.com: null
-stormsson@users.noreply.github.com: stormsson
-waxmann.sergiu@me.com: sergiuwaxmann
-web@ultralytics.com: UltralyticsAssistant
-xinwang614@gmail.com: GreatV
+116908874+jk4e@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/116908874?v=4
+  username: jk4e
+130829914+IvorZhu331@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/130829914?v=4
+  username: IvorZhu331
+135830346+UltralyticsAssistant@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/135830346?v=4
+  username: UltralyticsAssistant
+1579093407@qq.com:
+  avatar: https://avatars.githubusercontent.com/u/160490334?v=4
+  username: YOLOv5-Magic
+17216799+ouphi@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/17216799?v=4
+  username: ouphi
+17316848+maianumerosky@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/17316848?v=4
+  username: maianumerosky
+34196005+fcakyon@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/34196005?v=4
+  username: fcakyon
+37276661+capjamesg@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/37276661?v=4
+  username: capjamesg
+39910262+ChaoningZhang@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/39910262?v=4
+  username: ChaoningZhang
+40165666+berry-ding@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/40165666?v=4
+  username: berry-ding
+47978446+sergiuwaxmann@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/47978446?v=4
+  username: sergiuwaxmann
+48149018+zhixuwei@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/48149018?v=4
+  username: zhixuwei
+49699333+dependabot[bot]@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/27347476?v=4
+  username: dependabot[bot]
+53246858+hasanghaffari93@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/53246858?v=4
+  username: hasanghaffari93
+60036186+mfloto@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/60036186?v=4
+  username: mfloto
+61612323+Laughing-q@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/61612323?v=4
+  username: Laughing-q
+62214284+Burhan-Q@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/62214284?v=4
+  username: Burhan-Q
+68285002+Kayzwer@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/68285002?v=4
+  username: Kayzwer
+75611662+tensorturtle@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/75611662?v=4
+  username: tensorturtle
+78843978+Skillnoob@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/78843978?v=4
+  username: Skillnoob
+79740115+0xSynapse@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/79740115?v=4
+  username: 0xSynapse
+Francesco.mttl@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/3855193?v=4
+  username: ambitious-octopus
+abirami.vina@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/25847604?v=4
+  username: abirami-vina
+ahmelsamahy@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/10195309?v=4
+  username: Ahelsamahy
+andrei.kochin@intel.com:
+  avatar: https://avatars.githubusercontent.com/u/72827868?v=4
+  username: andrei-kochin
+ayush.chaurarsia@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/15766192?v=4
+  username: AyushExel
+chr043416@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/62513924?v=4
+  username: RizwanMunawar
+glenn.jocher@ultralytics.com:
+  avatar: https://avatars.githubusercontent.com/u/26833433?v=4
+  username: glenn-jocher
+hnliu_2@stu.xidian.edu.cn:
+  avatar: null
+  username: null
+jpedrofonseca_94@hotmail.com:
+  avatar: null
+  username: null
+k-2feng@hotmail.com:
+  avatar: null
+  username: null
+lakshanthad@yahoo.com:
+  avatar: https://avatars.githubusercontent.com/u/20147381?v=4
+  username: lakshanthad
+muhammadrizwanmunawar123@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/62513924?v=4
+  username: RizwanMunawar
+plashchynski@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/30833?v=4
+  username: plashchynski
+priytosh.revolution@live.com:
+  avatar: https://avatars.githubusercontent.com/u/19519529?v=4
+  username: priytosh-tripathi
+rulosanti@gmail.com:
+  avatar: null
+  username: null
+shuizhuyuanluo@126.com:
+  avatar: null
+  username: null
+sometimesocrazy@gmail.com:
+  avatar: null
+  username: null
+stormsson@users.noreply.github.com:
+  avatar: https://avatars.githubusercontent.com/u/1133032?v=4
+  username: stormsson
+xinwang614@gmail.com:
+  avatar: https://avatars.githubusercontent.com/u/17264618?v=4
+  username: GreatV

examples/heatmaps.ipynb

@@ -116,7 +116,7 @@
     "    colormap=cv2.COLORMAP_PARULA,\n",
     "    view_img=True,\n",
     "    shape=\"circle\",\n",
-    "    classes_names=model.names,\n",
+    "    names=model.names,\n",
     ")\n",
     "\n",
     "while cap.isOpened():\n",

examples/object_counting.ipynb

@@ -129,7 +129,7 @@
     "counter = solutions.ObjectCounter(\n",
     "    view_img=True,  # Display the image during processing\n",
     "    reg_pts=line_points,  # Region of interest points\n",
-    "    classes_names=model.names,  # Class names from the YOLO model\n",
+    "    names=model.names,  # Class names from the YOLO model\n",
     "    draw_tracks=True,  # Draw tracking lines for objects\n",
     "    line_thickness=2,  # Thickness of the lines drawn\n",
     ")\n",

pyproject.toml

@@ -71,6 +71,7 @@ dependencies = [
     "pyyaml>=5.3.1",
     "requests>=2.23.0",
     "scipy>=1.4.1",
+    "torch>=1.8.0,<2.4.0; sys_platform == 'win32'",  # Windows CPU errors https://github.com/ultralytics/ultralytics/issues/15049
     "torch>=1.8.0",
     "torchvision>=0.9.0",
     "tqdm>=4.64.0", # progress bars
@@ -93,7 +94,7 @@ dev = [
     "mkdocstrings[python]",
     "mkdocs-jupyter", # notebooks
     "mkdocs-redirects", # 301 redirects
-    "mkdocs-ultralytics-plugin>=0.1.2", # for meta descriptions and images, dates and authors
+    "mkdocs-ultralytics-plugin>=0.1.6", # for meta descriptions and images, dates and authors
     "mkdocs-macros-plugin>=1.0.5"  # duplicating content (i.e. export tables) in multiple places
 ]
 export = [

tests/test_explorer.py

@@ -5,9 +5,11 @@ import pytest
 
 from ultralytics import Explorer
 from ultralytics.utils import ASSETS
+from ultralytics.utils.torch_utils import TORCH_1_13
 
 
 @pytest.mark.slow
+@pytest.mark.skipif(not TORCH_1_13, reason="Explorer requires torch>=1.13")
 def test_similarity():
     """Test the correctness and response length of similarity calculations and SQL queries in the Explorer."""
     exp = Explorer(data="coco8.yaml")
@@ -25,6 +27,7 @@ def test_similarity():
 
 
 @pytest.mark.slow
+@pytest.mark.skipif(not TORCH_1_13, reason="Explorer requires torch>=1.13")
 def test_det():
     """Test detection functionalities and verify embedding table includes bounding boxes."""
     exp = Explorer(data="coco8.yaml", model="yolov8n.pt")
@@ -38,6 +41,7 @@ def test_det():
 
 
 @pytest.mark.slow
+@pytest.mark.skipif(not TORCH_1_13, reason="Explorer requires torch>=1.13")
 def test_seg():
     """Test segmentation functionalities and ensure the embedding table includes segmentation masks."""
     exp = Explorer(data="coco8-seg.yaml", model="yolov8n-seg.pt")
@@ -50,6 +54,7 @@ def test_seg():
 
 
 @pytest.mark.slow
+@pytest.mark.skipif(not TORCH_1_13, reason="Explorer requires torch>=1.13")
 def test_pose():
     """Test pose estimation functionality and verify the embedding table includes keypoints."""
     exp = Explorer(data="coco8-pose.yaml", model="yolov8n-pose.pt")

tests/test_python.py

@@ -252,6 +252,8 @@ def test_labels_and_crops():
     for r in results:
         im_name = Path(r.path).stem
         cls_idxs = r.boxes.cls.int().tolist()
+        # Check correct detections
+        assert cls_idxs == ([0, 0, 5, 0, 7] if r.path.endswith("bus.jpg") else [0, 0])  # bus.jpg and zidane.jpg classes
         # Check label path
         labels = save_path / f"labels/{im_name}.txt"
         assert labels.exists()

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.84"
+__version__ = "8.2.86"
 
 import os
 

ultralytics/data/converter.py

@@ -490,7 +490,7 @@ def convert_dota_to_yolo_obb(dota_root_path: str):
                 normalized_coords = [
                     coords[i] / image_width if i % 2 == 0 else coords[i] / image_height for i in range(8)
                 ]
-                formatted_coords = ["{:.6g}".format(coord) for coord in normalized_coords]
+                formatted_coords = [f"{coord:.6g}" for coord in normalized_coords]
                 g.write(f"{class_idx} {' '.join(formatted_coords)}\n")
 
     for phase in ["train", "val"]:

ultralytics/data/dataset.py

@@ -296,7 +296,7 @@ class GroundingDataset(YOLODataset):
         """Loads annotations from a JSON file, filters, and normalizes bounding boxes for each image."""
         labels = []
         LOGGER.info("Loading annotation file...")
-        with open(self.json_file, "r") as f:
+        with open(self.json_file) as f:
             annotations = json.load(f)
         images = {f'{x["id"]:d}': x for x in annotations["images"]}
         img_to_anns = defaultdict(list)

ultralytics/data/split_dota.py

@@ -193,7 +193,7 @@ def crop_and_save(anno, windows, window_objs, im_dir, lb_dir, allow_background_i
 
             with open(Path(lb_dir) / f"{new_name}.txt", "w") as f:
                 for lb in label:
-                    formatted_coords = ["{:.6g}".format(coord) for coord in lb[1:]]
+                    formatted_coords = [f"{coord:.6g}" for coord in lb[1:]]
                     f.write(f"{int(lb[0])} {' '.join(formatted_coords)}\n")
 
 

ultralytics/engine/exporter.py

@@ -138,7 +138,7 @@ def try_export(inner_func):
             LOGGER.info(f"{prefix} export success ✅ {dt.t:.1f}s, saved as '{f}' ({file_size(f):.1f} MB)")
             return f, model
         except Exception as e:
-            LOGGER.info(f"{prefix} export failure ❌ {dt.t:.1f}s: {e}")
+            LOGGER.error(f"{prefix} export failure ❌ {dt.t:.1f}s: {e}")
             raise e
 
     return outer_func
@@ -204,8 +204,8 @@ class Exporter:
             self.args.half = False
             assert not self.args.dynamic, "half=True not compatible with dynamic=True, i.e. use only one."
         self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2)  # check image size
-        if self.args.int8 and (engine or xml):
-            self.args.dynamic = True  # enforce dynamic to export TensorRT INT8; ensures ONNX is dynamic
+        if self.args.int8 and engine:
+            self.args.dynamic = True  # enforce dynamic to export TensorRT INT8
         if self.args.optimize:
             assert not ncnn, "optimize=True not compatible with format='ncnn', i.e. use optimize=False"
             assert self.device.type == "cpu", "optimize=True not compatible with cuda devices, i.e. use device='cpu'"
@@ -248,6 +248,7 @@ class Exporter:
                 m.dynamic = self.args.dynamic
                 m.export = True
                 m.format = self.args.format
+                m.max_det = self.args.max_det
             elif isinstance(m, C2f) and not is_tf_format:
                 # EdgeTPU does not support FlexSplitV while split provides cleaner ONNX graph
                 m.forward = m.forward_split
@@ -353,18 +354,20 @@ class Exporter:
         """Build and return a dataloader suitable for calibration of INT8 models."""
         LOGGER.info(f"{prefix} collecting INT8 calibration images from 'data={self.args.data}'")
         data = (check_cls_dataset if self.model.task == "classify" else check_det_dataset)(self.args.data)
+        # TensorRT INT8 calibration should use 2x batch size
+        batch = self.args.batch * (2 if self.args.format == "engine" else 1)
         dataset = YOLODataset(
             data[self.args.split or "val"],
             data=data,
             task=self.model.task,
             imgsz=self.imgsz[0],
             augment=False,
-            batch_size=self.args.batch * 2,  # NOTE TensorRT INT8 calibration should use 2x batch size
+            batch_size=batch,
         )
         n = len(dataset)
         if n < 300:
             LOGGER.warning(f"{prefix} WARNING ⚠️ >300 images recommended for INT8 calibration, found {n} images.")
-        return build_dataloader(dataset, batch=self.args.batch * 2, workers=0)  # required for batch loading
+        return build_dataloader(dataset, batch=batch, workers=0)  # required for batch loading
 
     @try_export
     def export_torchscript(self, prefix=colorstr("TorchScript:")):
@@ -420,7 +423,6 @@ class Exporter:
 
         # Checks
         model_onnx = onnx.load(f)  # load onnx model
-        # onnx.checker.check_model(model_onnx)  # check onnx model
 
         # Simplify
         if self.args.simplify:
@@ -430,10 +432,6 @@ class Exporter:
                 LOGGER.info(f"{prefix} slimming with onnxslim {onnxslim.__version__}...")
                 model_onnx = onnxslim.slim(model_onnx)
 
-                # ONNX Simplifier (deprecated as must be compiled with 'cmake' in aarch64 and Conda CI environments)
-                # import onnxsim
-                # model_onnx, check = onnxsim.simplify(model_onnx)
-                # assert check, "Simplified ONNX model could not be validated"
             except Exception as e:
                 LOGGER.warning(f"{prefix} simplifier failure: {e}")
 
@@ -677,7 +675,6 @@ class Exporter:
     def export_engine(self, prefix=colorstr("TensorRT:")):
         """YOLOv8 TensorRT export https://developer.nvidia.com/tensorrt."""
         assert self.im.device.type != "cpu", "export running on CPU but must be on GPU, i.e. use 'device=0'"
-        # self.args.simplify = True
         f_onnx, _ = self.export_onnx()  # run before TRT import https://github.com/ultralytics/ultralytics/issues/7016
 
         try:
@@ -784,7 +781,7 @@ class Exporter:
             # Load dataset w/ builder (for batching) and calibrate
             config.int8_calibrator = EngineCalibrator(
                 dataset=self.get_int8_calibration_dataloader(prefix),
-                batch=2 * self.args.batch,
+                batch=2 * self.args.batch,  # TensorRT INT8 calibration should use 2x batch size
                 cache=str(self.file.with_suffix(".cache")),
             )
 
@@ -867,8 +864,6 @@ class Exporter:
                 f.mkdir()
                 images = [batch["img"].permute(0, 2, 3, 1) for batch in self.get_int8_calibration_dataloader(prefix)]
                 images = torch.cat(images, 0).float()
-                # mean = images.view(-1, 3).mean(0)  # imagenet mean [123.675, 116.28, 103.53]
-                # std = images.view(-1, 3).std(0)  # imagenet std [58.395, 57.12, 57.375]
                 np.save(str(tmp_file), images.numpy().astype(np.float32))  # BHWC
                 np_data = [["images", tmp_file, [[[[0, 0, 0]]]], [[[[255, 255, 255]]]]]]
         else:
@@ -996,20 +991,7 @@ class Exporter:
         if " " in f:
             LOGGER.warning(f"{prefix} WARNING ⚠️ your model may not work correctly with spaces in path '{f}'.")
 
-        # f_json = Path(f) / 'model.json'  # *.json path
-        # with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
-        #     subst = re.sub(
-        #         r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
-        #         r'"Identity.?.?": {"name": "Identity.?.?"}, '
-        #         r'"Identity.?.?": {"name": "Identity.?.?"}, '
-        #         r'"Identity.?.?": {"name": "Identity.?.?"}}}',
-        #         r'{"outputs": {"Identity": {"name": "Identity"}, '
-        #         r'"Identity_1": {"name": "Identity_1"}, '
-        #         r'"Identity_2": {"name": "Identity_2"}, '
-        #         r'"Identity_3": {"name": "Identity_3"}}}',
-        #         f_json.read_text(),
-        #     )
-        #     j.write(subst)
+        # Add metadata
         yaml_save(Path(f) / "metadata.yaml", self.metadata)  # add metadata.yaml
         return f, None
 
@@ -1102,27 +1084,11 @@ class Exporter:
         names = self.metadata["names"]
         nx, ny = spec.description.input[0].type.imageType.width, spec.description.input[0].type.imageType.height
         _, nc = out0_shape  # number of anchors, number of classes
-        # _, nc = out0.type.multiArrayType.shape
         assert len(names) == nc, f"{len(names)} names found for nc={nc}"  # check
 
         # Define output shapes (missing)
         out0.type.multiArrayType.shape[:] = out0_shape  # (3780, 80)
         out1.type.multiArrayType.shape[:] = out1_shape  # (3780, 4)
-        # spec.neuralNetwork.preprocessing[0].featureName = '0'
-
-        # Flexible input shapes
-        # from coremltools.models.neural_network import flexible_shape_utils
-        # s = [] # shapes
-        # s.append(flexible_shape_utils.NeuralNetworkImageSize(320, 192))
-        # s.append(flexible_shape_utils.NeuralNetworkImageSize(640, 384))  # (height, width)
-        # flexible_shape_utils.add_enumerated_image_sizes(spec, feature_name='image', sizes=s)
-        # r = flexible_shape_utils.NeuralNetworkImageSizeRange()  # shape ranges
-        # r.add_height_range((192, 640))
-        # r.add_width_range((192, 640))
-        # flexible_shape_utils.update_image_size_range(spec, feature_name='image', size_range=r)
-
-        # Print
-        # print(spec.description)
 
         # Model from spec
         model = ct.models.MLModel(spec, weights_dir=weights_dir)

ultralytics/engine/predictor.py

@@ -328,7 +328,7 @@ class BasePredictor:
             frame = int(match[1]) if match else None  # 0 if frame undetermined
 
         self.txt_path = self.save_dir / "labels" / (p.stem + ("" if self.dataset.mode == "image" else f"_{frame}"))
-        string += "%gx%g " % im.shape[2:]
+        string += "{:g}x{:g} ".format(*im.shape[2:])
         result = self.results[i]
         result.save_dir = self.save_dir.__str__()  # used in other locations
         string += f"{result.verbose()}{result.speed['inference']:.1f}ms"

ultralytics/engine/validator.py

@@ -202,8 +202,9 @@ class BaseValidator:
             return {k: round(float(v), 5) for k, v in results.items()}  # return results as 5 decimal place floats
         else:
             LOGGER.info(
-                "Speed: %.1fms preprocess, %.1fms inference, %.1fms loss, %.1fms postprocess per image"
-                % tuple(self.speed.values())
+                "Speed: {:.1f}ms preprocess, {:.1f}ms inference, {:.1f}ms loss, {:.1f}ms postprocess per image".format(
+                    *tuple(self.speed.values())
+                )
             )
             if self.args.save_json and self.jdict:
                 with open(str(self.save_dir / "predictions.json"), "w") as f:

ultralytics/hub/utils.py

@@ -55,23 +55,22 @@ def request_with_credentials(url: str) -> any:
 
     display.display(
         display.Javascript(
-            """
-            window._hub_tmp = new Promise((resolve, reject) => {
+            f"""
+            window._hub_tmp = new Promise((resolve, reject) => {{
                 const timeout = setTimeout(() => reject("Failed authenticating existing browser session"), 5000)
-                fetch("%s", {
+                fetch("{url}", {{
                     method: 'POST',
                     credentials: 'include'
-                })
+                }})
                     .then((response) => resolve(response.json()))
-                    .then((json) => {
+                    .then((json) => {{
                     clearTimeout(timeout);
-                    }).catch((err) => {
+                    }}).catch((err) => {{
                     clearTimeout(timeout);
                     reject(err);
-                });
-            });
+                }});
+            }});
             """
-            % url
         )
     )
     return output.eval_js("_hub_tmp")

ultralytics/models/fastsam/predict.py

@@ -100,7 +100,7 @@ class FastSAMPredictor(SegmentationPredictor):
                     texts = [texts]
                 crop_ims, filter_idx = [], []
                 for i, b in enumerate(result.boxes.xyxy.tolist()):
-                    x1, y1, x2, y2 = [int(x) for x in b]
+                    x1, y1, x2, y2 = (int(x) for x in b)
                     if masks[i].sum() <= 100:
                         filter_idx.append(i)
                         continue

ultralytics/models/sam/modules/blocks.py

@@ -35,7 +35,7 @@ class DropPath(nn.Module):
 
     def __init__(self, drop_prob=0.0, scale_by_keep=True):
         """Initialize DropPath module for stochastic depth regularization during training."""
-        super(DropPath, self).__init__()
+        super().__init__()
         self.drop_prob = drop_prob
         self.scale_by_keep = scale_by_keep
 

ultralytics/nn/modules/block.py

@@ -672,7 +672,7 @@ class CBLinear(nn.Module):
 
     def __init__(self, c1, c2s, k=1, s=1, p=None, g=1):
         """Initializes the CBLinear module, passing inputs unchanged."""
-        super(CBLinear, self).__init__()
+        super().__init__()
         self.c2s = c2s
         self.conv = nn.Conv2d(c1, sum(c2s), k, s, autopad(k, p), groups=g, bias=True)
 
@@ -686,7 +686,7 @@ class CBFuse(nn.Module):
 
     def __init__(self, idx):
         """Initializes CBFuse module with layer index for selective feature fusion."""
-        super(CBFuse, self).__init__()
+        super().__init__()
         self.idx = idx
 
     def forward(self, xs):

ultralytics/nn/modules/head.py

@@ -144,12 +144,12 @@ class Detect(nn.Module):
             (torch.Tensor): Processed predictions with shape (batch_size, min(max_det, num_anchors), 6) and last
                 dimension format [x, y, w, h, max_class_prob, class_index].
         """
-        batch_size, anchors, predictions = preds.shape  # i.e. shape(16,8400,84)
+        batch_size, anchors, _ = preds.shape  # i.e. shape(16,8400,84)
         boxes, scores = preds.split([4, nc], dim=-1)
         index = scores.amax(dim=-1).topk(min(max_det, anchors))[1].unsqueeze(-1)
         boxes = boxes.gather(dim=1, index=index.repeat(1, 1, 4))
         scores = scores.gather(dim=1, index=index.repeat(1, 1, nc))
-        scores, index = scores.flatten(1).topk(max_det)
+        scores, index = scores.flatten(1).topk(min(max_det, anchors))
         i = torch.arange(batch_size)[..., None]  # batch indices
         return torch.cat([boxes[i, index // nc], scores[..., None], (index % nc)[..., None].float()], dim=-1)
 

ultralytics/solutions/parking_management.py

@@ -210,7 +210,7 @@ class ParkingManagement:
         Args:
             json_file (str): file that have all parking slot points
         """
-        with open(json_file, "r") as f:
+        with open(json_file) as f:
             return json.load(f)
 
     def process_data(self, json_data, im0, boxes, clss):

ultralytics/utils/benchmarks.py

@@ -198,7 +198,7 @@ class RF100Benchmark:
         os.mkdir("ultralytics-benchmarks")
         safe_download("https://github.com/ultralytics/assets/releases/download/v0.0.0/datasets_links.txt")
 
-        with open(ds_link_txt, "r") as file:
+        with open(ds_link_txt) as file:
             for line in file:
                 try:
                     _, url, workspace, project, version = re.split("/+", line.strip())
@@ -222,7 +222,7 @@ class RF100Benchmark:
         Args:
             path (str): YAML file path.
         """
-        with open(path, "r") as file:
+        with open(path) as file:
             yaml_data = yaml.safe_load(file)
         yaml_data["train"] = "train/images"
         yaml_data["val"] = "valid/images"
@@ -242,7 +242,7 @@ class RF100Benchmark:
         skip_symbols = ["🚀", "⚠️", "💡", "❌"]
         with open(yaml_path) as stream:
             class_names = yaml.safe_load(stream)["names"]
-        with open(val_log_file, "r", encoding="utf-8") as f:
+        with open(val_log_file, encoding="utf-8") as f:
             lines = f.readlines()
             eval_lines = []
             for line in lines:

ultralytics/utils/checks.py

@@ -29,11 +29,13 @@ from ultralytics.utils import (
     IS_PIP_PACKAGE,
     LINUX,
     LOGGER,
+    MACOS,
     ONLINE,
     PYTHON_VERSION,
     ROOT,
     TORCHVISION_VERSION,
     USER_CONFIG_DIR,
+    WINDOWS,
     Retry,
     SimpleNamespace,
     ThreadingLocked,
@@ -224,6 +226,14 @@ def check_version(
     if not required:  # if required is '' or None
         return True
 
+    if "sys_platform" in required:  # i.e. required='<2.4.0,>=1.8.0; sys_platform == "win32"'
+        if (
+            (WINDOWS and "win32" not in required)
+            or (LINUX and "linux" not in required)
+            or (MACOS and "macos" not in required and "darwin" not in required)
+        ):
+            return True
+
     op = ""
     version = ""
     result = True
@@ -422,6 +432,7 @@ def check_torchvision():
     """
     # Compatibility table
     compatibility_table = {
+        "2.4": ["0.19"],
         "2.3": ["0.18"],
         "2.2": ["0.17"],
         "2.1": ["0.16"],

ultralytics/utils/metrics.py

@@ -460,7 +460,7 @@ def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names={}, on_plot=N
     else:
         ax.plot(px, py, linewidth=1, color="grey")  # plot(recall, precision)
 
-    ax.plot(px, py.mean(1), linewidth=3, color="blue", label="all classes %.3f mAP@0.5" % ap[:, 0].mean())
+    ax.plot(px, py.mean(1), linewidth=3, color="blue", label=f"all classes {ap[:, 0].mean():.3f} mAP@0.5")
     ax.set_xlabel("Recall")
     ax.set_ylabel("Precision")
     ax.set_xlim(0, 1)

ultralytics/utils/ops.py

@@ -218,7 +218,7 @@ def non_max_suppression(
         classes = torch.tensor(classes, device=prediction.device)
 
     if prediction.shape[-1] == 6:  # end-to-end model (BNC, i.e. 1,300,6)
-        output = [pred[pred[:, 4] > conf_thres] for pred in prediction]
+        output = [pred[pred[:, 4] > conf_thres][:max_det] for pred in prediction]
         if classes is not None:
             output = [pred[(pred[:, 5:6] == classes).any(1)] for pred in output]
         return output

ultralytics/utils/torch_utils.py

@@ -1,4 +1,5 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
+
 import contextlib
 import gc
 import math
@@ -24,6 +25,7 @@ from ultralytics.utils import (
     NUM_THREADS,
     PYTHON_VERSION,
     TORCHVISION_VERSION,
+    WINDOWS,
     __version__,
     colorstr,
 )
@@ -42,6 +44,11 @@ TORCHVISION_0_10 = check_version(TORCHVISION_VERSION, "0.10.0")
 TORCHVISION_0_11 = check_version(TORCHVISION_VERSION, "0.11.0")
 TORCHVISION_0_13 = check_version(TORCHVISION_VERSION, "0.13.0")
 TORCHVISION_0_18 = check_version(TORCHVISION_VERSION, "0.18.0")
+if WINDOWS and torch.__version__[:3] == "2.4":  # reject all versions of 2.4 on Windows
+    LOGGER.warning(
+        "WARNING ⚠️ Known issue with torch>=2.4.0 on Windows with CPU, recommend downgrading to torch<=2.3.1 to resolve "
+        "https://github.com/ultralytics/ultralytics/issues/15049"
+    )
 
 
 @contextmanager