Deploy latest YOLO model and app (version 20250422.7)

README.md

@@ -4,7 +4,6 @@ emoji: 🧬
 colorFrom: blue
 colorTo: indigo
 sdk: gradio
-sdk_version: "4.26.0"
 app_file: app.py
 pinned: false
 ---
@@ -33,6 +32,7 @@ python app.py
 
 3. Deploy to [Hugging Face Spaces](https://huggingface.co/spaces):
    - Push this directory to a new Space as a Gradio app.
+   - If you update dependencies, restart the Space from the web UI to ensure a clean rebuild.
 
 ## Usage
 
@@ -46,16 +46,17 @@ python app.py
 - `deploy.sh` automates model update and Hugging Face Space deployment, with Git LFS support.
 
 ## Integration
-- Replace the dummy `segment` function in `app.py` with your YOLO model inference code.
-- The API will accept an image and return a segmentation mask (as an image).
+- The API will accept an image and return a segmentation mask (as an image) and the model version as a string.
+- For annotation tool integration (e.g., CVAT), see the [NOTES.md](../NOTES.md) for design decisions and API tips.
 
 ## Notes
 - Add any additional dependencies to `requirements.txt` as needed.
-- For Spaces, ensure your model weights are included or downloadable.
+- For Spaces, ensure your model weights are included or downloadable (Git LFS required for files >10MB).
+- If you change requirements.txt, restart the Space from the Hugging Face UI ("Restart from Scratch") to ensure dependency updates are applied.
 
 ## Citation & Context
 
-This tool is part of the Swinburne DECam synthetic data and galaxy segmentation research project. For scientific use, please cite appropriately and refer to the project thesis for detailed methodology and rationale.
+This tool is part of the Swinburne DECam synthetic data and orbital streak segmentation research project. For scientific use, please cite appropriately and refer to the project thesis and [NOTES.md](../NOTES.md) for detailed methodology and rationale.
 
 ---
 

runtime.txt

@@ -0,0 +1 @@
+python-3.11