| --- |
| pipeline_tag: object-detection |
| license: apache-2.0 |
| base_model: ustc-community/dfine-medium-coco |
| library_name: zeromodels |
| tags: |
| - keras |
| - zeromodels |
| - d-fine |
| - dfine |
| - detr |
| - object-detection |
| - arxiv:2410.13842 |
| - pytorch |
| - jax |
| - tf |
| --- |
| |
| ## ***See [our collection](https://huggingface.co/collections/zeromodels/d-fine-6a8eaf8bc6d10755c3e14a80) for all versions of D-FINE.*** |
|
|
| # Run D-FINE with Keras 3: JAX, PyTorch, or TensorFlow |
|
|
| [](https://github.com/IMvision12/ZeroModels) [](https://imvision12.github.io/ZeroModels/dfine/) [](https://huggingface.co/collections/zeromodels/d-fine-6a8eaf8bc6d10755c3e14a80) |
|
|
| # zeromodels/dfine-medium |
|
|
| Paper: [D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement (arXiv:2410.13842)](https://arxiv.org/abs/2410.13842) · [HF Papers](https://huggingface.co/papers/2410.13842) |
|
|
| D-FINE is a real-time detector built on the RT-DETR recipe: an HGNetV2 backbone, a hybrid encoder, and a deformable decoder with 300 queries. It is NMS-free. Boxes are regressed via Fine-grained Distribution Refinement: each decoder layer predicts a distribution over discrete offset bins and accumulates refinements across layers. |
|
|
| For more details on the model, please go to the upstream [model card](https://huggingface.co/ustc-community/dfine-medium-coco). |
|
|
| Pure-**Keras 3** conversion of [`ustc-community/dfine-medium-coco`](https://huggingface.co/ustc-community/dfine-medium-coco) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**. |
|
|
| This is an **object detection** checkpoint (`DFineDetect`) on COCO (HGNetV2-Medium). |
|
|
| ## ✨ Quick start |
|
|
| ```python |
| import os |
| os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow" |
| |
| from PIL import Image |
| from zeromodels.models.dfine import DFineDetect, DFineImageProcessor |
| |
| model = DFineDetect.from_weights("zeromodels/dfine-medium") |
| processor = DFineImageProcessor.from_weights("zeromodels/dfine-medium") |
| |
| image = Image.open("your_image.jpg").convert("RGB") |
| inputs = processor(image) |
| output = model(inputs["pixel_values"], training=False) |
| results = processor.post_process_object_detection( |
| output, threshold=0.5, target_sizes=[(image.height, image.width)] |
| )[0] |
| for score, name, box in zip( |
| results["scores"], results["label_names"], results["boxes"] |
| ): |
| print(f"{name}: {float(score):.3f} {box}") |
| ``` |
|
|
| Load any D-FINE variant the same way with `from_weights("zeromodels/<variant>")`: |
|
|
| | Variant | Hub | Backbone | |
| |---|---|---| |
| | `dfine-nano` | [`zeromodels/dfine-nano`](https://huggingface.co/zeromodels/dfine-nano) | HGNetV2-Nano | |
| | `dfine-small` | [`zeromodels/dfine-small`](https://huggingface.co/zeromodels/dfine-small) | HGNetV2-Small | |
| | `dfine-medium` | [`zeromodels/dfine-medium`](https://huggingface.co/zeromodels/dfine-medium) | HGNetV2-Medium | |
| | `dfine-large` | [`zeromodels/dfine-large`](https://huggingface.co/zeromodels/dfine-large) | HGNetV2-Large | |
| | `dfine-xlarge` | [`zeromodels/dfine-xlarge`](https://huggingface.co/zeromodels/dfine-xlarge) | HGNetV2-XLarge | |
|
|
| ## Tips |
|
|
| - Set `KERAS_BACKEND` **before** importing Keras / zeromodels. |
| - `DFineImageProcessor` keeps `do_normalize=False` by default (rescaled `[0, 1]` input, matching upstream). |
| - See [D-FINE docs](https://imvision12.github.io/ZeroModels/dfine/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/). |
| - Community / upstream safetensors still work via the `hf:` prefix, e.g. `DFineDetect.from_weights("hf:ustc-community/dfine-medium-coco")`. |
|
|
| ## Special Thanks |
|
|
| A huge thank you to the D-FINE authors (USTC community) for creating and releasing these models. |
|
|
| License: Apache 2.0. |
|
|
