Push model using huggingface_hub.

README.md

@@ -3,78 +3,9 @@ license: apache-2.0
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
-language:
-- en
-pipeline_tag: keypoint-detection
 ---
 
-# DETRPose-L-COCO
-
-DETRPose-L-COCO is a real-time object detection model introduced in the paper [DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints](https://huggingface.co/papers/2506.13027). 
-
-- **Repository:** [https://github.com/SebastianJanampa/DETRPose](https://github.com/SebastianJanampa/DETRPose)
-- **Paper:** [https://huggingface.co/papers/2506.13027](https://huggingface.co/papers/2506.13027)
-
-## 📝 Model Description
-DETRPose introduces the first real-time end-to-end framework for multi-person pose estimation. 
-By leveraging the hybrid encoder from RT-DETR and the lightweight decoder architecture of D-FINE, DETRPose achieves low-latency inference without sacrificing accuracy.
-The model introduces two primary methodological advancements:
-
-* **Pose-LQE Layer:** A specialized head designed to improve confidence scores.
-* **Advanced Training Paradigm:** Incorporates Denoising Keypoints and a custom Keypoint Similarity Varifocal loss function, ensuring robust learning and superior localization performance.
-
-
-| Model | Dataset | AP | #Params | Latency | GFLOPs |
-| :---: | :---: | :---: | :---: | :---: | :---: |
-| **DETRPose-L** | COCO | 72.5 | 32.8 M | 9.50 ms | 107.1 |
-
-
-## 🚀 Installation
-
-To use this model, you need to install the inference-ready branch of the DETRPose repository.
-You can directly install the inference-ready branch using `pip`:
-```shell
-pip install git+https://github.com/SebastianJanampa/DETRPose.git@inference_only
-````
-
-## 💻 Usage
-This branch is designed to be easy to use for inference. 
-Here is a quick example of how to load a model and run it on a live webcam feed.
-```python
-from detrpose import DETR
-
-# Initialization
-model = DETR(model='detrpose_hgnetv2_l')
-
-# Inference
-model(source=0) # inference on a webcam
-```
-
-
-## 📜 Citation
-If you use `DETRPose` or its methods in your work, please cite the following BibTeX entries:
-
-```latex
-@misc{janampa2025detrpose,
-      title={DETRPose: Real-time end-to-end transformer model for multi-person pose estimation}, 
-      author={Sebastian Janampa and Marios Pattichis},
-      year={2025},
-      eprint={2506.13027},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV},
-      url={https://arxiv.org/abs/2506.13027}, 
-}
-```
-
-## 🙏 Acknowledgement
-This work was supported in part by [Lambda.ai](https://lambda.ai).
-
-Our work is built upon [DEIM](https://github.com/Intellindust-AI-Lab/DEIM/tree/main), [D-FINE](https://github.com/Peterande/D-FINE), [Detectron2](https://github.com/facebookresearch/detectron2/tree/main), and [GroupPose](https://github.com/Michel-liu/GroupPose/tree/main).
-
-✨ Feel free to reach out if you have any questions! ✨
-
-<div align="left">
-  <a href="https://lambda.ai" target="_blank">
-  	<img src="./assets/lambda_logo2.png" width=500 >
-  </a>
-</div>
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: [More Information Needed]
+- Paper: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -15,7 +15,35 @@
       ],
       "use_lab": false
     },
-    "decoder": {
+    "encoder": {
+      "_target_": "detrpose.nn.DETRPoseHybridEncoder",
+      "act": "silu",
+      "depth_mult": 1.0,
+      "dim_feedforward": 1024,
+      "dropout": 0.0,
+      "enc_act": "gelu",
+      "eval_spatial_size": [
+        640,
+        640
+      ],
+      "expansion": 1.0,
+      "feat_strides": [
+        8,
+        16,
+        32
+      ],
+      "hidden_dim": 256,
+      "in_channels": [
+        512,
+        1024,
+        2048
+      ],
+      "num_heads": 8,
+      "num_levels": 3,
+      "temperatureH": 20,
+      "temperatureW": 20
+    },
+    "transformer": {
       "_target_": "detrpose.nn.DETRPoseTransformer",
       "activation": "relu",
       "cls_no_bias": false,
@@ -48,34 +76,6 @@
       "two_stage_bbox_embed_share": false,
       "two_stage_class_embed_share": false,
       "two_stage_type": "standard"
-    },
-    "encoder": {
-      "_target_": "detrpose.nn.DETRPoseHybridEncoder",
-      "act": "silu",
-      "depth_mult": 1.0,
-      "dim_feedforward": 1024,
-      "dropout": 0.0,
-      "enc_act": "gelu",
-      "eval_spatial_size": [
-        640,
-        640
-      ],
-      "expansion": 1.0,
-      "feat_strides": [
-        8,
-        16,
-        32
-      ],
-      "hidden_dim": 256,
-      "in_channels": [
-        512,
-        1024,
-        2048
-      ],
-      "num_heads": 8,
-      "num_levels": 3,
-      "temperatureH": 20,
-      "temperatureW": 20
     }
   },
   "postprocessor": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5339012117ac626bc7208a96bbaeb7916e57781945225ad5404ce50ed5285fe4
-size 133799740
+oid sha256:b5c2acd3dde633114ae6fbc9b2e7ef16e01735d0d34928c55e87cefc0566432c
+size 133800348