Add YOLO11 Models to Zoo #4899
Add YOLO11 Models to Zoo #4899
Conversation
WalkthroughThe pull request updates the FiftyOne documentation and functionality to support additional YOLO models, specifically YOLOv11. It includes new commented-out code snippets for loading various YOLOv11 models in the documentation, as well as enhancements in the Changes
Possibly related PRs
Suggested reviewers
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Outside diff range and nitpick comments (1)
docs/source/integrations/ultralytics.rst (1)
108-114: LGTM! Consider adding a brief comment about YOLO11.The addition of YOLO11 models is consistent with the PR objectives and follows the correct naming convention. To improve clarity for users, consider adding a brief comment above the YOLO11 section, similar to the comments for other YOLO versions.
# YOLOv10 # model = YOLO("yolov10n.pt) # model = YOLO("yolov10s.pt) # model = YOLO("yolov10m.pt) # model = YOLO("yolov10l.pt) # model = YOLO("yolov10x.pt) + # YOLO11 (latest version with improved performance) # YOLOv11 # model = YOLO("yolo11n.pt) # model = YOLO("yolo11s.pt) # model = YOLO("yolo11m.pt) # model = YOLO("yolo11l.pt) # model = YOLO("yolo11x.pt)
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
⛔ Files ignored due to path filters (1)
fiftyone/zoo/models/manifest-torch.jsonis excluded by!**/*.json
📒 Files selected for processing (2)
- docs/source/integrations/ultralytics.rst (4 hunks)
- fiftyone/utils/ultralytics.py (0 hunks)
💤 Files with no reviewable changes (1)
- fiftyone/utils/ultralytics.py
🔇 Additional comments (2)
docs/source/integrations/ultralytics.rst (2)
150-150: LGTM! YOLO11 Model Zoo integration looks good.The addition of the YOLO11x model to the Model Zoo section is consistent with the PR objectives and follows the correct naming convention.
193-197: LGTM! YOLO11 segmentation models added correctly.The addition of YOLO11 segmentation models is consistent with the PR objectives and follows the correct naming convention. The inclusion of only s, m, l, and x variants aligns with the PR summary about including only models with superior performance.
| You can also load YOLOv8, YOLOv9, and YOLO11 segmentation models from the | ||
| :ref:`FiftyOne Model Zoo <model-zoo>`: | ||
|
|
||
| .. code-block:: python | ||
| :linenos: | ||
|
|
||
| model_name = "yolov9c-seg-coco-torch" | ||
| # model_name = "yolov9e-seg-coco-torch" | ||
| # model_name = "yolov8x-seg-coco-torch" | ||
| # model_name = "yolov8l-seg-coco-torch" | ||
| # model_name = "yolov8m-seg-coco-torch" | ||
| model_name = "yolov8n-seg-coco-torch" | ||
| # model_name = "yolov8s-seg-coco-torch" | ||
| # model_name = "yolov8n-seg-coco-torch" | ||
| # model_name = "yolov8m-seg-coco-torch" | ||
| # model_name = "yolov8l-seg-coco-torch" | ||
| # model_name = "yolov8x-seg-coco-torch" | ||
|
|
||
| # model_name = "yolov9c-seg-coco-torch" | ||
| # model_name = "yolov9e-seg-coco-torch" | ||
|
|
||
| # model_name = "yolo11n-seg-coco-torch" | ||
| # model_name = "yolo11s-seg-coco-torch" | ||
| # model_name = "yolo11m-seg-coco-torch" | ||
| # model_name = "yolo11l-seg-coco-torch" | ||
| # model_name = "yolo11x-seg-coco-torch" | ||
|
|
There was a problem hiding this comment.
💡 Codebase verification
Inconsistent Inclusion of yolo11n-seg Model
The yolo11n-seg-coco-torch model is included in the Model Zoo section but is absent from the Instance Segmentation section. Please ensure that yolo11n-seg is consistently referenced across all relevant sections to maintain clarity and completeness.
- Verify if
yolo11n-segshould be available in the Instance Segmentation section. - Update the Instance Segmentation section accordingly to include or exclude
yolo11n-seg.
🔗 Analysis chain
LGTM with a minor inconsistency.
The addition of YOLO11 segmentation models to the Model Zoo section is consistent with the PR objectives and follows the correct naming convention. However, there's a minor inconsistency:
- The
yolo11n-segmodel is included here but not in the previous instance segmentation section. - The PR summary states that only models demonstrating superior performance are included.
Please verify if the yolo11n-seg model should be included, and ensure consistency across all sections.
To verify the inclusion of the yolo11n-seg model, please run the following script:
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check for the presence of yolo11n-seg model in different sections
# Check in the instance segmentation section
echo "Checking instance segmentation section:"
sed -n '/Instance segmentation/,/You can also load/p' docs/source/integrations/ultralytics.rst | grep -i 'yolo11.*-seg'
echo -e "\nChecking Model Zoo section:"
# Check in the Model Zoo section
sed -n '/You can also load.*segmentation models/,/model = foz.load_zoo_model/p' docs/source/integrations/ultralytics.rst | grep -i 'yolo11.*-seg'
Length of output: 797
What changes are proposed in this pull request?
Adds YOLO11 detection and segmentation models to the zoo manifest and the integration docs.
Note that unlike previous yolo models, which included a "v" in the name, they do away with that here. So instead of "yolov11n", it is "yolo11n".
Only detection and segmentation models are explicitly added to the zoo because these are the only ones (not the OBB, classification, and pose) which have superior performance to yolov8.
Release Notes
Is this a user-facing change that should be mentioned in the release notes?
notes for FiftyOne users.
YOLO11 detection and segmentation models added to the model zoo, bringing significant inference speedups on TensorRT compared to previous yolo models
What areas of FiftyOne does this PR affect?
fiftyonePython library changesSummary by CodeRabbit
New Features
Documentation