Upload app.py with huggingface_hub

app.py

@@ -1,9 +1,10 @@
-"""Chart Pattern Detection API — YOLOv8 on HuggingFace Spaces"""
+"""Chart Pattern Detection API — YOLOv8"""
 import gradio as gr
 import torch
 import json
+import traceback
 
-# Fix PyTorch 2.6+ weights_only default change
+# Fix PyTorch 2.6+ weights_only default
 _original_load = torch.load
 def _patched_load(*args, **kwargs):
     if "weights_only" not in kwargs:
@@ -11,38 +12,42 @@ def _patched_load(*args, **kwargs):
     return _original_load(*args, **kwargs)
 torch.load = _patched_load
 
-from ultralyticsplus import YOLO
+from ultralytics import YOLO
+from huggingface_hub import hf_hub_download
 
-model = YOLO("foduucom/stockmarket-pattern-detection-yolov8")
-model.overrides["conf"] = 0.25
-model.overrides["iou"] = 0.45
+# Download and load model
+model_path = hf_hub_download(repo_id="foduucom/stockmarket-pattern-detection-yolov8", filename="model.pt")
+model = YOLO(model_path)
 
 def detect_patterns(image):
-    if image is None:
-        return json.dumps({"patterns": [], "error": "No image"})
-    results = model.predict(image)
-    patterns = []
-    for r in results:
-        boxes = r.boxes
-        for i in range(len(boxes)):
-            box = boxes[i]
-            cls_id = int(box.cls[0])
-            conf = float(box.conf[0])
-            xyxy = box.xyxy[0].tolist()
-            label = r.names[cls_id]
-            patterns.append({
-                "label": label,
-                "confidence": round(conf, 3),
-                "bbox": [round(x, 1) for x in xyxy],
-            })
-    patterns.sort(key=lambda p: p["confidence"], reverse=True)
-    return json.dumps({"patterns": patterns, "count": len(patterns)})
+    try:
+        if image is None:
+            return json.dumps({"patterns": [], "error": "No image"})
+        results = model.predict(source=image, conf=0.25, iou=0.45, verbose=False)
+        patterns = []
+        for r in results:
+            if r.boxes is None:
+                continue
+            for i in range(len(r.boxes)):
+                box = r.boxes[i]
+                cls_id = int(box.cls[0])
+                conf = float(box.conf[0])
+                xyxy = box.xyxy[0].tolist()
+                label = r.names[cls_id]
+                patterns.append({
+                    "label": label,
+                    "confidence": round(conf, 3),
+                    "bbox": [round(x, 1) for x in xyxy],
+                })
+        patterns.sort(key=lambda p: p["confidence"], reverse=True)
+        return json.dumps({"patterns": patterns, "count": len(patterns)})
+    except Exception as e:
+        return json.dumps({"patterns": [], "error": str(e), "trace": traceback.format_exc()})
 
 demo = gr.Interface(
     fn=detect_patterns,
     inputs=gr.Image(type="pil", label="Chart Image"),
     outputs=gr.Textbox(label="Detected Patterns (JSON)"),
     title="Chart Pattern Detection — YOLOv8",
-    description="Detects: Head & Shoulders (Top/Bottom), Double Top/Bottom, Triangles, Trend Lines",
 )
-demo.launch()
+demo.launch(show_error=True)