Deploy latest YOLO model and app (version 20250422.7)

README.md

@@ -0,0 +1,28 @@
+# YOLO Segmentation Model Server (Gradio)
+
+This subproject provides a Gradio web app and API endpoint for your YOLO segmentation model.
+
+## Quickstart
+
+1. Install dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+2. Run the server locally:
+
+```bash
+python app.py
+```
+
+3. Deploy to [Hugging Face Spaces](https://huggingface.co/spaces):
+   - Push this directory to a new Space as a Gradio app.
+
+## 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).
+
+## Notes
+- Add any additional dependencies to `requirements.txt` as needed.
+- For Spaces, ensure your model weights are included or downloadable.

VERSION

@@ -0,0 +1 @@
+20250422.7

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+from PIL import Image
+from pathlib import Path
+import numpy as np
+import torch
+from ultralytics import YOLO
+import os
+
+MODEL_WEIGHTS_PATH = Path("weights/best.pt")  # Path to model weights (populated by deploy.sh)
+VERSION_PATH = Path("VERSION")
+
+# Read version string from VERSION file
+try:
+    VERSION = VERSION_PATH.read_text().strip()
+except Exception:
+    VERSION = "unknown"
+
+# Lazy-load model (singleton)
+model = None
+def get_model():
+    global model
+    if model is None:
+        if not MODEL_WEIGHTS_PATH.exists():
+            raise FileNotFoundError(f"Model weights not found at {MODEL_WEIGHTS_PATH}. Please deploy weights before running.")
+        model = YOLO(str(MODEL_WEIGHTS_PATH))
+    return model
+
+def segment(image: Image.Image):
+    model = get_model()
+    img_np = np.array(image)
+    # Run prediction
+    results = model(img_np)
+    if not results or not hasattr(results[0], "masks") or results[0].masks is None:
+        mask_img = Image.new("L", image.size, 0)  # Blank mask if no detections
+    else:
+        mask = results[0].masks.data[0].cpu().numpy()  # (H, W) binary mask
+        mask_img = Image.fromarray((mask * 255).astype(np.uint8))
+        mask_img = mask_img.resize(image.size)  # Ensure mask matches input size
+    # Return both the mask and version in the API response
+    return {"mask": mask_img, "version": VERSION}
+
+iface = gr.Interface(
+    fn=segment,
+    inputs=gr.Image(type="pil"),
+    outputs=[gr.Image(type="pil", label="Segmentation Mask"), gr.Textbox(label="Model Version")],
+    title=f"YOLO Segmentation Model (version: {VERSION})",
+    description=f"Upload an image to get a segmentation mask. Model version: {VERSION}"
+)
+
+if __name__ == "__main__":
+    iface.launch()

deploy.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+# Usage: ./deploy.sh <path_to_latest_yolo_train_dir> <hf_space_git_url>
+# Example: ./deploy.sh ../yolo-output/models/20250422.7/ https://huggingface.co/spaces/<user>/<space_name>.git
+
+set -e
+
+if [ $# -lt 1 ]; then
+  echo "Usage: $0 <path_to_latest_yolo_train_dir>"
+  exit 1
+fi
+
+MODEL_DIR=$1
+[email protected]:spaces/rayh/clusterflux
+MODEL_SERVER_DIR=$(dirname "$0")
+WEIGHTS_SRC="$MODEL_DIR/train/weights/best.pt"
+WEIGHTS_DST="$MODEL_SERVER_DIR/weights/best.pt"
+
+# Step 1: Copy model weights
+mkdir -p "$MODEL_SERVER_DIR/weights"
+cp "$WEIGHTS_SRC" "$WEIGHTS_DST"
+echo "Copied model weights from $WEIGHTS_SRC to $WEIGHTS_DST"
+
+# Step 2: Extract version (last part of model dir)
+VERSION=$(basename "$MODEL_DIR")
+echo "$VERSION" > "$MODEL_SERVER_DIR/VERSION"
+echo "Set VERSION to $VERSION"
+
+# Step 3: Deploy to Hugging Face Spaces
+echo "Pushing to Hugging Face Space..."
+cd "$MODEL_SERVER_DIR"
+if [ ! -d .git ]; then
+  git init
+  git remote add origin "$HF_SPACE_URL"
+fi
+git add .
+git commit -m "Deploy latest YOLO model and app (version $VERSION)" || echo "Nothing to commit"
+git branch -M main
+git push -u origin main --force
+
+echo "Deployment complete."

requirements.txt

@@ -0,0 +1,5 @@
+gradio>=4.0.0
+pillow
+# Add your model dependencies below, e.g.:
+ultralytics
+torch