latest

app.py

@@ -11,32 +11,21 @@ from transformers import Sam3Model, Sam3Processor
 import warnings
 warnings.filterwarnings("ignore")
 
-# Global variables for lazy initialization
-_model = None
-_processor = None
-_device = None
-
-def get_model_and_processor():
-    """Lazy initialization of model and processor"""
-    global _model, _processor, _device
-    if _model is None:
-        _device = "cuda" if torch.cuda.is_available() else "cpu"
-        _model = Sam3Model.from_pretrained(
-            "facebook/sam3",
-            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
-        ).to(_device)
-        _processor = Sam3Processor.from_pretrained("facebook/sam3")
-        print(f"Model loaded on device: {_device}")
-    return _model, _processor, _device
-
 @spaces.GPU
 def sam3_inference(image, text_prompt, confidence_threshold=0.5):
     """
-    Standalone GPU function with lazy model initialization for Spaces Stateless GPU
+    Standalone GPU function with model initialization for Spaces Stateless GPU
+    All CUDA operations must happen inside this decorated function
     """
     try:
-        # Initialize model inside GPU function (required for Stateless GPU)
-        model, processor, device = get_model_and_processor()
+        # Initialize model and processor inside GPU function (required for Stateless GPU)
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        model = Sam3Model.from_pretrained(
+            "facebook/sam3",
+            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
+        ).to(device)
+        processor = Sam3Processor.from_pretrained("facebook/sam3")
+        print(f"Model loaded on device: {device}")
 
         # Handle base64 input (for API)
         if isinstance(image, str):