fix temp file

vr180_matting/sam2_wrapper.py

@@ -89,9 +89,10 @@ class SAM2VideoMatting:
             if video_frames is None or len(video_frames) == 0:
                 raise ValueError("Either video_path or video_frames must be provided")
             
-            # Create temporary video file
-            temp_dir = tempfile.mkdtemp()
-            temp_video_path = Path(temp_dir) / "temp_video.mp4"
+            # Create temporary video file in current directory
+            import uuid
+            temp_video_name = f"temp_sam2_{uuid.uuid4().hex[:8]}.mp4"
+            temp_video_path = Path.cwd() / temp_video_name
             
             # Write frames to temporary video
             height, width = video_frames[0].shape[:2]
@@ -266,8 +267,8 @@ class SAM2VideoMatting:
         if self.temp_video_path is not None:
             try:
                 if self.temp_video_path.exists():
-                    # Remove the temporary directory
-                    shutil.rmtree(self.temp_video_path.parent)
+                    # Remove the temporary video file
+                    self.temp_video_path.unlink()
                 self.temp_video_path = None
             except Exception as e:
                 warnings.warn(f"Failed to cleanup temp video: {e}")

vr180_matting/vr180_processor.py

@@ -150,52 +150,75 @@ class VR180Processor(VideoProcessor):
         if not eye_frames:
             return []
         
-        # Initialize SAM2 with eye frames
-        self.sam2_model.init_video_state(eye_frames)
+        # Create a unique temporary video for this eye processing
+        import uuid
+        temp_video_name = f"temp_sam2_{eye_name}_chunk{chunk_idx}_{uuid.uuid4().hex[:8]}.mp4"
+        temp_video_path = Path.cwd() / temp_video_name
         
-        # Detect persons in first frame
-        first_frame = eye_frames[0]
-        detections = self.detector.detect_persons(first_frame)
-        
-        if not detections:
-            warnings.warn(f"No persons detected in {eye_name} eye, chunk {chunk_idx}")
-            return self._create_empty_masks(eye_frames)
-        
-        print(f"Detected {len(detections)} persons in {eye_name} eye first frame")
-        
-        # Convert to SAM2 prompts
-        box_prompts, labels = self.detector.convert_to_sam_prompts(detections)
-        
-        # Add prompts
-        object_ids = self.sam2_model.add_person_prompts(0, box_prompts, labels)
-        
-        # Propagate masks
-        video_segments = self.sam2_model.propagate_masks(
-            start_frame=0, 
-            max_frames=len(eye_frames)
-        )
-        
-        # Apply masks
-        matted_frames = []
-        for frame_idx, frame in enumerate(eye_frames):
-            if frame_idx in video_segments:
-                frame_masks = video_segments[frame_idx]
-                combined_mask = self.sam2_model.get_combined_mask(frame_masks)
-                
-                matted_frame = self.sam2_model.apply_mask_to_frame(
-                    frame, combined_mask,
-                    output_format=self.config.output.format,
-                    background_color=self.config.output.background_color
-                )
-            else:
-                matted_frame = self._create_empty_mask_frame(frame)
+        try:
+            # Write frames to temporary video
+            height, width = eye_frames[0].shape[:2]
+            fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+            writer = cv2.VideoWriter(str(temp_video_path), fourcc, 30.0, (width, height))
             
-            matted_frames.append(matted_frame)
-        
-        # Cleanup
-        self.sam2_model.cleanup()
-        
-        return matted_frames
+            for frame in eye_frames:
+                writer.write(frame)
+            writer.release()
+            
+            # Initialize SAM2 with video path
+            self.sam2_model.init_video_state(video_path=str(temp_video_path))
+            
+            # Detect persons in first frame
+            first_frame = eye_frames[0]
+            detections = self.detector.detect_persons(first_frame)
+            
+            if not detections:
+                warnings.warn(f"No persons detected in {eye_name} eye, chunk {chunk_idx}")
+                return self._create_empty_masks(eye_frames)
+            
+            print(f"Detected {len(detections)} persons in {eye_name} eye first frame")
+            
+            # Convert to SAM2 prompts
+            box_prompts, labels = self.detector.convert_to_sam_prompts(detections)
+            
+            # Add prompts
+            object_ids = self.sam2_model.add_person_prompts(0, box_prompts, labels)
+            
+            # Propagate masks
+            video_segments = self.sam2_model.propagate_masks(
+                start_frame=0, 
+                max_frames=len(eye_frames)
+            )
+            
+            # Apply masks
+            matted_frames = []
+            for frame_idx, frame in enumerate(eye_frames):
+                if frame_idx in video_segments:
+                    frame_masks = video_segments[frame_idx]
+                    combined_mask = self.sam2_model.get_combined_mask(frame_masks)
+                    
+                    matted_frame = self.sam2_model.apply_mask_to_frame(
+                        frame, combined_mask,
+                        output_format=self.config.output.format,
+                        background_color=self.config.output.background_color
+                    )
+                else:
+                    matted_frame = self._create_empty_mask_frame(frame)
+                
+                matted_frames.append(matted_frame)
+            
+            return matted_frames
+            
+        finally:
+            # Always cleanup
+            self.sam2_model.cleanup()
+            
+            # Remove temporary video file
+            try:
+                if temp_video_path.exists():
+                    temp_video_path.unlink()
+            except Exception as e:
+                warnings.warn(f"Failed to cleanup temp video {temp_video_path}: {e}")
     
     def _process_eye_sequence_with_validation(self, 
                                             right_eye_frames: List[np.ndarray],