--- language: - en license: unknown library_name: mmdetection pipeline_tag: object-detection inference: false datasets: - detection-datasets/coco tags: - object-detection - co-detr - co-deformable-detr - detr - coco - swin - mmdetection - pytorch - iccv2023 model-index: - name: co_deformable_detr_swin_base_1x_coco results: - task: type: object-detection dataset: name: COCO 2017 val type: coco split: val2017 metrics: - type: box AP value: 55.5 name: box AP --- # Co-Deformable-DETR (Swin-B, 1x (12 epochs), COCO)
## 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](#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](#citation)) and use the [official repository](https://github.com/Sense-X/Co-DETR) or the maintained fork [`dronefreak/Co-DETR`](https://github.com/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-deformable-detr-swin-b-1x-coco \ co_deformable_detr_swin_base_1x_coco.pth co_deformable_detr_swin_base_1x_coco.py \ --local-dir checkpoints/ # 3. Run detection on an image / folder / video / webcam python tools/inference.py \ --config checkpoints/co_deformable_detr_swin_base_1x_coco.py \ --checkpoint checkpoints/co_deformable_detr_swin_base_1x_coco.pth \ --input demo/demo.jpg --out-dir outputs/ --save-json ``` The bundled config is identical to `projects/configs/co_deformable_detr/co_deformable_detr_swin_base_1x_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-Deformable-DETR query head runs and the RPN / RoI / ATSS heads add no inference-time computation to the deployed detector. **This checkpoint** is Co-Deformable-DETR (two-stage, with iterative box refinement) with a **Swin-B** backbone: | | | |---|---| | Detector | `CoDETR` meta-model; deployed head is `CoDeformDETRHead` | | Backbone | Swin-B, pretrained on ImageNet-22k | | Object queries | 300 | | Aux heads in state-dict | `RPNHead` + `CoStandardRoIHead`, `CoATSSHead`: present in the weights but **not executed at inference** (`eval_module='detr'`) | | Parameters | 109.4 M executed at inference (backbone + neck + query head). The checkpoint additionally stores the training-only RPN / RoI / ATSS heads (125.7 M total), which inference never touches. | | Classes | 80 (COCO `things`) | | Training schedule | COCO `train2017`, 1x (12 epochs) | | Test-time input | single scale, no flip / no TTA (the config's test pipeline; see [Measured inference footprint](#measured-inference-footprint) for the actual resized size on the sample image) | - **Paper**: [DETRs with Collaborative Hybrid Assignments Training](https://arxiv.org/abs/2211.12860), ICCV 2023 - **Config**: [`co_deformable_detr_swin_base_1x_coco.py`](co_deformable_detr_swin_base_1x_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 **55.5 box AP is the authors' number; I have not reproduced it** (see [Evaluation](#evaluation-as-reported-by-the-original-authors)). - **No real-time claim.** See [measured latency](#measured-inference-footprint) 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 55.5 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 | **109.4 M** | | Params stored in the checkpoint | 125.7 M | | Test image | `demo/demo.jpg` -> 800 x 1199 fed to backbone | | Peak `max_memory_allocated` | 1073 MiB (1.13 GB) | | Peak `max_memory_reserved` | 1388 MiB (1.46 GB) | | Latency / image (warm, n=10) | mean 113 ms (110-117) | 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 | 55.5 | Co-DETR paper (arXiv:2211.12860) / official model zoo | **No** | Schedule: 1x (12 epochs), 300 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](https://arxiv.org/abs/1405.0312)). - Backbone initialization: Swin-B pretrained on ImageNet-22k. I do **not** redistribute COCO here. Get it from [cocodataset.org](https://cocodataset.org/#download). 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](https://github.com/Sense-X/Co-DETR/blob/main/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](https://github.com/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](https://github.com/open-mmlab/mmdetection) / [MMCV](https://github.com/open-mmlab/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_deformable_detr_swin_base_1x_coco.pth`, 507,002,799 bytes, SHA-256 `e9e1a0a9845f1ed2a0d799385aa9e5bd83481d9e8dbc2ed97324c50d6af303bc`. I copied it byte-for-byte and unmodified from the authors' Google Drive folder `1asWoZ3SuM6APTL9D-QUF_YW9mjULNdh9`. Repo files: `co_deformable_detr_swin_base_1x_coco.pth` (weights), `co_deformable_detr_swin_base_1x_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.