Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Remove deepsparse integration #1164

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jun 22, 2025
+335 −10,840
Merged

Remove deepsparse integration #1164

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
440401e
Remove deepsparse integration
fcakyon Jun 22, 2025
3e0be54
add support to pycocotools >= 2.0.9
fcakyon Jun 22, 2025
e098c89
Update CI dependencies for PyTorch and torchvision to support macOS
fcakyon Jun 22, 2025
52eb5ac
Refactor JSON handling to ensure 'info' field is added if missing and…
fcakyon Jun 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,3 +169,4 @@ tests/data

.archive
.python-version
uv.lock
2 changes: 0 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,8 +91,6 @@ Object detection and instance segmentation are by far the most important applica

- `RT-DETR` + `SAHI` walkthrough: <a href="https://colab.research.google.com/github/obss/sahi/blob/main/demo/inference_for_rtdetr.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="sahi-rtdetr"></a> (NEW)

- `DeepSparse` + `SAHI` walkthrough: <a href="https://colab.research.google.com/github/obss/sahi/blob/main/demo/inference_for_sparse_yolov5.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="sahi-deepsparse"></a>

- `HuggingFace` + `SAHI` walkthrough: <a href="https://colab.research.google.com/github/obss/sahi/blob/main/demo/inference_for_huggingface.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="sahi-huggingface"></a>

- `YOLOv5` + `SAHI` walkthrough: <a href="https://colab.research.google.com/github/obss/sahi/blob/main/demo/inference_for_yolov5.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="sahi-yolov5"></a>
Expand Down
870 changes: 0 additions & 870 deletions demo/inference_for_sparse_yolov5.ipynb
View file
Open in desktop

This file was deleted.

1 change: 0 additions & 1 deletion docs/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,6 @@ All documentation files are complemented by interactive Jupyter notebooks in the
- `inference_for_huggingface.ipynb` - HuggingFace models integration
- `inference_for_torchvision.ipynb` - TorchVision models integration
- `inference_for_rtdetr.ipynb` - RT-DETR integration
- `inference_for_sparse_yolov5.ipynb` - DeepSparse optimized inference

## Getting Started

Expand Down
1 change: 0 additions & 1 deletion docs/predict.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,5 @@ Want to see these prediction utilities in action? We have several interactive no
- For HuggingFace models, see our [HuggingFace integration notebook](../demo/inference_for_huggingface.ipynb)
- For TorchVision models, explore our [TorchVision integration notebook](../demo/inference_for_torchvision.ipynb)
- For RT-DETR models, check out our [RT-DETR integration notebook](../demo/inference_for_rtdetr.ipynb)
- For optimized inference with DeepSparse, see our [DeepSparse integration notebook](../demo/inference_for_sparse_yolov5.ipynb)

These notebooks provide hands-on examples and allow you to experiment with different parameters and settings.
16 changes: 10 additions & 6 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,16 +55,20 @@ dev = [
]
ci = [
# pytorch should be present for all python versions
"torch==2.6.0+cpu;python_version>='3.12'",
"torchvision==0.21.0+cpu;python_version>='3.12'",
"torch==2.1.2+cpu;python_version<'3.12'",
"torchvision==0.16.2+cpu;python_version<'3.12'",
# CPU versions for Linux/Windows CI
"torch==2.6.0+cpu;python_version>='3.12' and platform_system!='Darwin'",
"torchvision==0.21.0+cpu;python_version>='3.12' and platform_system!='Darwin'",
"torch==2.1.2+cpu;python_version<'3.12' and platform_system!='Darwin'",
"torchvision==0.16.2+cpu;python_version<'3.12' and platform_system!='Darwin'",
# Regular versions for macOS
"torch==2.6.0;python_version>='3.12' and platform_system=='Darwin'",
"torchvision==0.21.0;python_version>='3.12' and platform_system=='Darwin'",
"torch==2.1.2;python_version<'3.12' and platform_system=='Darwin'",
"torchvision==0.16.2;python_version<'3.12' and platform_system=='Darwin'",
# mmdet is supported for python<3.12
"mmengine;python_version<'3.12'",
"mmcv==2.1.0;python_version<'3.12'",
"mmdet==3.3.0;python_version<'3.12'",
# deepsparse is only available for python<3.12
"deepsparse;python_version<'3.12'",
"onnxruntime<1.20;python_version<'3.12'",
"onnx>1.16;python_version>='3.12'",
"onnxruntime;python_version>='3.12'",
Expand Down
1 change: 0 additions & 1 deletion sahi/auto_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@
"detectron2": "Detectron2DetectionModel",
"huggingface": "HuggingfaceDetectionModel",
"torchvision": "TorchVisionDetectionModel",
"yolov5sparse": "Yolov5SparseDetectionModel",
"yolov8onnx": "Yolov8OnnxDetectionModel",
}

Expand Down
221 changes: 0 additions & 221 deletions sahi/models/yolov5sparse.py
View file
Open in desktop

This file was deleted.

Loading
Loading