Update app.py

app.py

@@ -8,16 +8,12 @@ import insightface
 # Load Models (CPU mode)
 # ----------------------------
 
-yolo = YOLO("yolov8n.pt")  # lightweight model
+yolo = YOLO("yolov8n.pt")
 
 face_model = insightface.app.FaceAnalysis(name="buffalo_l")
-face_model.prepare(ctx_id=-1)  # -1 forces CPU (important for HF free tier)
+face_model.prepare(ctx_id=-1)
 
 
-# ----------------------------
-# Utility: Normalize embedding
-# ----------------------------
-
 def normalize(vec):
     vec = np.array(vec, dtype=np.float32)
     norm = np.linalg.norm(vec)
@@ -26,33 +22,23 @@ def normalize(vec):
     return (vec / norm).tolist()
 
 
-# ----------------------------
-# Main Processing Function
-# ----------------------------
-
 def process_image(image):
     image_np = np.array(image)
-
     results = yolo(image_np)
-
     faces_output = []
 
     for r in results:
         boxes = r.boxes
 
         for box, cls, conf in zip(boxes.xyxy, boxes.cls, boxes.conf):
-
-            # YOLO class 0 = person
             if int(cls) != 0:
                 continue
-
             if float(conf) < 0.4:
                 continue
 
             xmin, ymin, xmax, ymax = box.cpu().numpy()
             xmin, ymin, xmax, ymax = map(int, [xmin, ymin, xmax, ymax])
 
-            # Safety check for valid crop
             h, w, _ = image_np.shape
             xmin = max(0, xmin)
             ymin = max(0, ymin)
@@ -60,17 +46,13 @@ def process_image(image):
             ymax = min(h, ymax)
 
             person_crop = image_np[ymin:ymax, xmin:xmax]
-
             if person_crop.size == 0:
                 continue
 
-            # Detect face inside person crop
             detected_faces = face_model.get(person_crop)
 
             for face in detected_faces:
                 embedding = normalize(face.embedding)
-
-                # Adjust face bbox to original image coordinates
                 fxmin, fymin, fxmax, fymax = face.bbox.astype(int)
 
                 faces_output.append({
@@ -89,14 +71,18 @@ def process_image(image):
     return faces_output
 
 
-# ----------------------------
-# Gradio Interface
-# ----------------------------
-
 iface = gr.Interface(
     fn=process_image,
     inputs=gr.Image(type="pil"),
     outputs="json"
 )
 
-iface.launch()
+# 🔥 CRITICAL PART
+iface.queue(False)
+
+iface.launch(
+    server_name="0.0.0.0",
+    server_port=7860,
+    ssr_mode=False,
+    share=False
+)