Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+example1.jpg filter=lfs diff=lfs merge=lfs -text
+example2.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,26 @@
 ---
-title: Detrpose
-emoji: 🐠
-colorFrom: red
-colorTo: green
+title: DETRPose
+emoji: 🏃
+colorFrom: purple
+colorTo: yellow
 sdk: gradio
-sdk_version: 6.20.0
-python_version: '3.12'
+sdk_version: 6.15.1
 app_file: app.py
-pinned: false
+short_description: Real-time multi-person pose estimation with DETRPose-L
+python_version: "3.12"
+startup_duration_timeout: 30m
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# DETRPose: Real-Time Multi-Person Pose Estimation
+
+This Space demonstrates **DETRPose-L**, a real-time end-to-end transformer model for
+multi-person pose estimation. Upload an image and the model will detect all persons
+and overlay 17-keypoint COCO skeleton poses.
+
+## Model
+
+- **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)
+- **Weights**: [SebasJanampa/DETRPose_L_COCO](https://huggingface.co/SebasJanampa/DETRPose_L_COCO)
+- **GitHub**: [SebastianJanampa/DETRPose](https://github.com/SebastianJanampa/DETRPose)
+- **AP**: 72.5 on COCO val2017 | **Params**: 32.8M | **Latency**: 9.50ms (V100, FP16, TensorRT)

app.py

@@ -0,0 +1,117 @@
+import spaces  # MUST come before torch / any CUDA-touching import
+import torch
+import torchvision.transforms as T
+import gradio as gr
+import numpy as np
+import cv2
+from PIL import Image
+from copy import deepcopy
+from detrpose import DETR
+
+# Load the model at module scope, .to("cuda") eagerly.
+model = DETR(model="detrpose_hgnetv2_l", device="cuda")
+
+transforms = T.Compose(
+    [
+        T.Resize((640, 640)),
+        T.ToTensor(),
+    ]
+)
+
+
+@spaces.GPU(duration=60)
+def predict(image: "Image.Image", threshold: float = 0.5) -> "Image.Image":
+    """Detect multi-person poses in an image using DETRPose-L.
+
+    Args:
+        image: Input PIL image.
+        threshold: Confidence threshold for keeping detected poses.
+    """
+    if image is None:
+        return None
+
+    im_pil = image.convert("RGB")
+
+    w, h = im_pil.size
+    orig_size = torch.tensor([[w, h]]).to("cuda")
+
+    im_data = transforms(im_pil).unsqueeze(0).to("cuda")
+
+    with torch.no_grad():
+        outputs = model.model.model(im_data)
+        results = model.model.postprocessor(outputs, orig_size)
+
+    scores, labels, keypoints = results
+    scores = scores[0].detach().cpu().numpy()
+    keypoints = keypoints[0].detach().cpu().numpy()
+
+    idx = scores > threshold
+    valid_keypoints = keypoints[idx]
+
+    im_cv2 = cv2.cvtColor(np.array(im_pil), cv2.COLOR_RGB2BGR)
+    model.annotator.draw_on(im_cv2, valid_keypoints)
+
+    result_rgb = cv2.cvtColor(im_cv2, cv2.COLOR_BGR2RGB)
+    return Image.fromarray(result_rgb)
+
+
+CSS = """
+#col-container { max-width: 1100px; margin: 0 auto; }
+.dark .gradio-container { color: var(--body-text-color); }
+"""
+
+with gr.Blocks(theme=gr.themes.Citrus(), css=CSS) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(
+            "# DETRPose: Real-Time Multi-Person Pose Estimation\n"
+            "Upload an image to detect human poses with skeleton keypoints overlaid. "
+            "Powered by [DETRPose-L](https://huggingface.co/SebasJanampa/DETRPose_L_COCO) — "
+            "the first real-time end-to-end transformer for multi-person pose estimation."
+        )
+
+        with gr.Row():
+            with gr.Column(scale=1):
+                input_image = gr.Image(
+                    type="pil", label="Input Image", sources=["upload", "clipboard"]
+                )
+                threshold_slider = gr.Slider(
+                    minimum=0.1,
+                    maximum=0.9,
+                    value=0.5,
+                    step=0.05,
+                    label="Confidence Threshold",
+                )
+                run_btn = gr.Button("Run", variant="primary")
+
+            with gr.Column(scale=1):
+                output_image = gr.Image(
+                    type="pil", label="Pose Estimation Result"
+                )
+
+        with gr.Accordion("Advanced settings", open=False):
+            gr.Markdown(
+                "**Confidence Threshold**: Lower this to detect more poses (may include "
+                "false positives). Raise it for stricter, more confident detections."
+            )
+
+        gr.Examples(
+            examples=[
+                ["example1.jpg", 0.5],
+                ["example2.jpg", 0.5],
+            ],
+            inputs=[input_image, threshold_slider],
+            outputs=output_image,
+            fn=predict,
+            cache_examples=True,
+            cache_mode="lazy",
+        )
+
+    run_btn.click(
+        fn=predict,
+        inputs=[input_image, threshold_slider],
+        outputs=output_image,
+        api_name="predict",
+    )
+
+if __name__ == "__main__":
+    demo.launch(mcp_server=True)

requirements.txt

@@ -0,0 +1,9 @@
+opencv-python
+omegaconf
+cloudpickle
+iopath
+scipy
+loguru
+safetensors
+torchvision
+git+https://github.com/SebastianJanampa/DETRPose.git@inference_only