Deploy latest YOLO model and app (version 20250422.7)

app.py

@@ -2,11 +2,9 @@ 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)
+MODEL_WEIGHTS_PATH = Path("weights/best.pt")
 VERSION_PATH = Path("VERSION")
 
 # Read version string from VERSION file
@@ -15,9 +13,11 @@ try:
 except Exception:
     VERSION = "unknown"
 
-# Lazy-load model (singleton)
 model = None
-def get_model():
+def get_model() -> YOLO:
+    """
+    Returns the YOLO model instance.
+    """
     global model
     if model is None:
         if not MODEL_WEIGHTS_PATH.exists():
@@ -25,19 +25,20 @@ def get_model():
         model = YOLO(str(MODEL_WEIGHTS_PATH))
     return model
 
-def segment(image: Image.Image):
+def segment(image: Image.Image) -> tuple[Image.Image, str]:
+    """
+    Returns a tuple: (segmentation mask PIL.Image, model version string)
+    """
     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
+        mask_img = Image.new("L", image.size, 0)
     else:
-        mask = results[0].masks.data[0].cpu().numpy()  # (H, W) binary mask
+        mask = results[0].masks.data[0].cpu().numpy()
         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_img, VERSION  # Return as tuple for Gradio
+        mask_img = mask_img.resize(image.size)
+    return mask_img, str(VERSION)
 
 iface = gr.Interface(
     fn=segment,