Upload folder using huggingface_hub

README.md

@@ -1,32 +1,5 @@
----
-title: csPWS Nuclei Segmentation
-emoji: 🧬
-colorFrom: indigo
-colorTo: green
-sdk: gradio
-sdk_version: 5.43.1
-app_file: app.py
-pinned: true
----
+# csPWS Nuclei Segmentation — Space
 
-# csPWS Nuclei Segmentation — Hugging Face Space
-
-This Space runs **nuclei segmentation** for **chromatin-sensitive Partial Wave Spectroscopic (csPWS) microscopy** images using an **ONNX** model and a lightweight **Gradio** UI.
-
-## How to Use
-1. Upload a fused csPWS composite (Σ, BF, SW → RGB).
-2. The model returns a **binary mask** (white = nuclei).
-3. Download/save the mask for downstream chromatin analysis.
-
-## Behind the Scenes
-- **Model:** U-Net + Attention (exported to ONNX, INT8 quant supported)
-- **Runtime:** ONNX Runtime (CPU by default; CoreML if available)
-- **UI:** Gradio
-
-## Notes
-- This demo is trained on **synthetic** data; real csPWS generalization will be added later.
-- For PyTorch checkpoint mode, add `torch` to requirements and launch with `--ckpt` in `scripts/gradio_app.py`.
-
-## Links
-- **Model repo:** https://huggingface.co/jahidularafat/cspws-unet-attn
-- **Space repo:** https://huggingface.co/spaces/jahidularafat/cspws-space
+This Space runs an ONNX model for nuclei segmentation from csPWS composites.
+- Upload fused Σ/BF/SW image → segmentation mask + overlay
+- Auto-picks `model.int8.onnx` > `model.sim.onnx` > `model.onnx` at runtime

app.py

@@ -1,13 +1,3 @@
-import os, sys
-from pathlib import Path
-if (Path("scripts") / "gradio_app.py").exists():
-    sys.path.append(str(Path("scripts").absolute()))
-    from gradio_app import main
-    if __name__ == "__main__":
-        os.system("python scripts/gradio_app.py --onnx model.onnx --channels 3 --img-size 256 --port 7860")
-else:
-    import gradio as gr
-    def hello(x): return x
-    demo = gr.Interface(fn=hello, inputs="image", outputs="image", title="csPWS Fallback App")
-    if __name__ == "__main__":
-        demo.launch(server_port=7860)
+from scripts.gradio_app import main
+if __name__ == "__main__":
+    main()

model.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe3d43a2d19a4b8eb46d7cbf591c63541b8085c00437cff30cde8797bcbc1d5
+size 39925272

model.sim.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c2aae2d08ca1802202c43fcdfb50119c632816f190d05a66efd045f65eec09
+size 125544999

requirements.txt

@@ -1,5 +1,4 @@
+onnxruntime>=1.17.0
 gradio>=4.0.0
-onnxruntime>=1.18.0
-onnx>=1.15.0
+Pillow
 numpy
-pillow