Modelpublic

dronefreak/co-dino-5scale-lsj-swin-l-3x-coco

sourceHugging Faceunknownupdated 18d agoView on Hugging Face

0likes30downloads

Model Card

Co-DINO (Swin-L, 3x (36 epochs), COCO)

<video controls autoplay loop muted playsinline width="900" poster="https://huggingface.co/dronefreak/co-dino-5scale-lsj-swin-l-3x-coco/resolve/main/assets/demobannerposter.jpg" src="https://huggingface.co/dronefreak/co-dino-5scale-lsj-swin-l-3x-coco/resolve/main/assets/demobanner.mp4"><img src="https://huggingface.co/dronefreak/co-dino-5scale-lsj-swin-l-3x-coco/resolve/main/assets/demobanner_poster.jpg" alt="Co-DINO Swin-L detections on two dashcam clips" width="900"></video>

Disclaimer

This is not an official release. All credit for the method, the architecture, and the trained weights belongs entirely to the original authors: Zhuofan Zong, Guanglu Song, and Yu Liu (SenseTime X-Lab). I claim no contribution to the underlying research or training. I host the same checkpoint the authors published to Google Drive, with a model card and a copy of its config file.

Mirror rationale

The original non-ViT Co-DETR checkpoints are distributed through a single shared Google Drive folder, which is inconvenient for automated and reproducible downloads (no per-file addressing, checksums, or versioning). The authors published their ViT-L checkpoints to the Hub but not the ResNet-50 / Swin ones. I mirror this checkpoint to provide stable artifact hosting, an explicit file checksum (see Provenance), and versioned Hub access.

I mirror only the pretrained weights; I do not redistribute any training or evaluation data. I will transfer or remove this mirror at the original authors' request. Please cite the original paper (see Citation) and use the official repository or the maintained fork `dronefreak/Co-DETR` for code.

Quickstart

This is not a plain-PyTorch / transformers model. Inference needs the Co-DETR project code and the OpenMMLab 1.x stack (MMDetection 2.25.3, MMCV-full 1.5.0, PyTorch 1.11). The maintained fork ships a one-command environment setup for exactly this.

bash

# 1. Get the code + a validated environment
git clone https://github.com/dronefreak/Co-DETR && cd Co-DETR
bash tools/setup_codetr_env.sh          # builds the `codetr` conda env
conda activate codetr

# 2. Pull this checkpoint + its config from the Hub
pip install -U "huggingface_hub[cli]"
hf download dronefreak/co-dino-5scale-lsj-swin-l-3x-coco \
    co_dino_5scale_lsj_swin_large_3x_coco.pth co_dino_5scale_lsj_swin_large_3x_coco.py \
    --local-dir checkpoints/

# 3. Run detection on an image / folder / video / webcam
python tools/inference.py \
    --config checkpoints/co_dino_5scale_lsj_swin_large_3x_coco.py \
    --checkpoint checkpoints/co_dino_5scale_lsj_swin_large_3x_coco.pth \
    --input demo/demo.jpg --out-dir outputs/ --save-json

The bundled config is identical to projects/configs/co_dino/co_dino_5scale_lsj_swin_large_3x_coco.py in the repo.

What is Co-DETR / this checkpoint

Co-DETR ("DETRs with Collaborative Hybrid Assignments Training") is a training scheme, not a new architecture. It attaches auxiliary heads that use one-to-many label assignment (an ATSS head and a Faster-R-CNN-style RoI head) alongside the DETR decoder's one-to-one Hungarian matching, and feeds the positive proposals those heads produce back into the decoder as extra queries. This makes the encoder's features more discriminative and speeds up convergence. The auxiliary heads are used only during training: this checkpoint's config sets eval_module='detr', so at inference only the Co-DINO query head runs and the RPN / RoI / ATSS heads add no inference-time computation to the deployed detector.

This checkpoint is Co-DINO (5 feature scales, large-scale jitter (LSJ)) with a Swin-L backbone:


Detector	`CoDETR` meta-model; deployed head is `CoDINOHead`
Backbone	Swin-L, pretrained on ImageNet-22k
Object queries	900
Aux heads in state-dict	`RPNHead` + `CoStandardRoIHead`, `CoATSSHead`: present in the weights but not executed at inference (`eval_module='detr'`)
Parameters	219.2 M executed at inference (backbone + neck + query head). The checkpoint additionally stores the training-only RPN / RoI / ATSS heads (235.5 M total), which inference never touches.
Classes	80 (COCO `things`)
Training schedule	COCO `train2017`, 3x (36 epochs)
Test-time input	single scale, no flip / no TTA (the config's test pipeline; see Measured inference footprint for the actual resized size on the sample image)

—Paper: DETRs with Collaborative Hybrid Assignments Training, ICCV 2023
—Config: `co_dino_5scale_lsj_swin_large_3x_coco.py` (bundled; identical to the Co-DETR repo copy)

Intended use & limitations

Intended use. Research and engineering work that needs a COCO-pretrained object detector in the Co-DETR family: as a baseline, a feature/detection backbone, or a starting point for fine-tuning on a custom COCO-format dataset.

Limitations.

—Trained and evaluated on COCO only; predicts the 80 COCO `thing` categories and nothing else.
—Accuracy can degrade substantially on domain-shifted imagery (aerial, medical, document, non-natural images, etc.).
—The reported 60.7 box AP is the authors' number; I have not reproduced it (see Evaluation).
—No real-time claim. See measured latency for actual timings I got on one GPU.
—Runs only on the legacy OpenMMLab 1.x stack (MMDetection 2.25.3 / MMCV-full 1.5.0 / PyTorch 1.11); no transformers / pipeline() support, and inference: false on the Hub.
—The auxiliary training heads in the checkpoint are not exposed as inference outputs; only the DETR query head's detections are returned.

What I checked

Integrity and "does it load and run" checks only. This is not an accuracy reproduction:

—It loads with a full state-dict key match in the codetr env (Python 3.8 / torch 1.11.0+cu113 / mmcv-full 1.5.0 / mmdet 2.25.3): zero missing, zero unexpected keys.
—I ran it end-to-end through tools/inference.py on the two dashcam clips shown in the banner above; it produced valid annotated outputs.
—I did not re-measure COCO AP; the 60.7 box AP below is the authors' number.

Measured inference footprint

Method. I built the model with mmdet.apis.init_detector, then ran inference_detector() on a single image, device='cuda:0', batch size 1, FP32 (no AMP), cudnn.benchmark=False: one warm-up call, then torch.cuda.reset_peak_memory_stats() and 10 timed calls with torch.cuda.synchronize(). max_memory_allocated includes the resident model weights plus activation buffers; it excludes the CUDA context.

Item	Value
GPU	NVIDIA GeForce RTX 4070 SUPER, 12 GB, driver 580.173.02
Stack	Python 3.8, torch 1.11.0+cu113, mmcv-full 1.5.0, mmdet 2.25.3
Precision / batch	FP32 / 1
Params executed at inference	219.2 M
Params stored in the checkpoint	235.5 M
Test image	`demo/demo.jpg` -> 1280 x 1280 fed to backbone
Peak `max_memory_allocated`	3071 MiB (3.22 GB)
Peak `max_memory_reserved`	4562 MiB (4.78 GB)
Latency / image (warm, n=10)	mean 480 ms (478-482)

CPU inference (--device cpu) also works and needs no GPU; it is slower.

Evaluation (as reported by the original authors)

Benchmark	Metric	Value	Source	Reproduced here?
COCO `val2017`	box AP	60.7	Co-DETR paper (arXiv:2211.12860) / official model zoo	No

Schedule: 3x (36 epochs), 900 object queries, single-scale test, no TTA. I have not independently re-measured these numbers.

Training data

—COCO 2017 train2017: 118k images, 80 things categories. Lin et al., Microsoft COCO: Common Objects in Context, ECCV 2014 (arXiv:1405.0312).
—Backbone initialization: Swin-L pretrained on ImageNet-22k.

I do not redistribute COCO here. Get it from cocodataset.org. This checkpoint was trained using COCO and ImageNet initialization only; no Objects365 pretraining is described for it.

License status

The Co-DETR source code is MIT-licensed (© 2022 SenseTime X-Lab, LICENSE). The upstream repository does not provide a separate, explicit license for this checkpoint's weights. The original authors have published other Co-DETR checkpoints (the ViT-L family) on Hugging Face with MIT metadata, but I do not treat that as definitive evidence that these weights are independently licensed under MIT.

Because the applicable rights are undetermined, I set the Hub metadata for this repo to license: unknown. Verify the applicable rights yourself before redistribution or commercial use.

If you are one of the original authors and want this mirror removed or transferred, open an issue on this repo or contact dronefreak and I will action it.

Citation

bibtex

@inproceedings{zong2023detrs,
  title={DETRs with Collaborative Hybrid Assignments Training},
  author={Zong, Zhuofan and Song, Guanglu and Liu, Yu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages={6748--6758},
  year={2023}
}

The underlying detector and backbone:

bibtex

@inproceedings{zhu2021deformable,
  title={Deformable DETR: Deformable Transformers for End-to-End Object Detection},
  author={Zhu, Xizhou and Su, Weijie and Lu, Lewei and Li, Bin and Wang, Xiaogang and Dai, Jifeng},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2021}
}
@inproceedings{liu2021swin,
  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021}
}

Built with MMDetection / MMCV (OpenMMLab).

Acknowledgements

I sincerely thank Zhuofan Zong, Guanglu Song, and Yu Liu for developing Co-DETR and releasing the pretrained weights, and the OpenMMLab team for MMDetection and MMCV. This mirror only makes one of their existing checkpoints easier and more reliable to obtain.

Provenance

co_dino_5scale_lsj_swin_large_3x_coco.pth, 2,830,384,110 bytes, SHA-256 bc301b0b291843316b8f924f13bbd92825232dd30cd274712d044d40082a0f61. I copied it byte-for-byte and unmodified from the authors' Google Drive folder 1nAXOkzqrEgz-YnXxIEs4d5j9li_kmrnv.

Repo files: co_dino_5scale_lsj_swin_large_3x_coco.pth (weights), co_dino_5scale_lsj_swin_large_3x_coco.py (the MMDetection config needed to build the model), config.json (metadata summary; also what the Hub uses to count downloads), plus assets/demo_banner.mp4 / assets/demo_banner_poster.jpg for the card. config.json is descriptive only, inference: false, and is not a transformers config.