Update app.py

app.py

@@ -1,4 +1,5 @@
 # app.py — Gradio app for panoramic radiograph segmentation (Detectron2)
+
 import os, json, time, cv2, numpy as np, torch, gradio as gr
 from detectron2.config import get_cfg
 from detectron2.engine import DefaultPredictor
@@ -6,9 +7,9 @@ from detectron2.data import MetadataCatalog
 from detectron2.utils.visualizer import Visualizer, ColorMode
 
 # --- Local artifacts (uploaded to this Space) ---
-LOAD_DIR = "./artifacts"
-WEIGHTS = f"{LOAD_DIR}/model_final.pth"
-CFG_PATH = f"{LOAD_DIR}/config.yaml"
+LOAD_DIR   = "./artifacts"
+WEIGHTS    = f"{LOAD_DIR}/model_final.pth"
+CFG_PATH   = f"{LOAD_DIR}/config.yaml"
 CLASSES_PATH = f"{LOAD_DIR}/classes.json"
 
 # --- Build cfg & load model ---
@@ -42,16 +43,16 @@ def segment(rgb: np.ndarray):
     else:
         rgb_small = rgb
 
-    outputs = predictor(rgb_small[:, :, ::-1])  # BGR
+    # Detectron2 expects BGR; our array is RGB
+    outputs = predictor(rgb_small[:, :, ::-1])
     inst = outputs["instances"].to("cpu")
 
     vis = Visualizer(rgb_small, metadata=meta, scale=1.0, instance_mode=ColorMode.IMAGE_BW)
-    vis = vis.draw_instance_predictions(inst)
-    overlay_rgb = vis.get_image()
+    overlay_rgb = vis.draw_instance_predictions(inst).get_image()
 
     dets = []
     boxes_small = inst.pred_boxes.tensor.numpy().tolist() if inst.has("pred_boxes") else []
-    scores = inst.scores.numpy().tolist() if inst.has("scores") else []
+    scores      = inst.scores.numpy().tolist() if inst.has("scores") else []
     classes_idx = inst.pred_classes.numpy().tolist() if inst.has("pred_classes") else []
     inv = (1.0/scale) if scale != 1.0 else 1.0
     for b, s, c in zip(boxes_small, scores, classes_idx):
@@ -71,7 +72,8 @@ with gr.Blocks(title="Panoramic Radiograph Segmentation") as demo:
     with gr.Row():
         img_out = gr.Image(label="Overlay")
         json_out = gr.JSON(label="Detections (boxes in original image coords)")
+    # Keep a stable API route for future programmatic calls
     gr.Button("Run").click(segment, inputs=img_in, outputs=[img_out, json_out], api_name="/predict")
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()  # no share=True on Spaces