The following error occurred when I ran app. py：IndexError: too many indices for tensor of dimension 1

[Bentonmaster]

  File "/home/gcbm/workspace/Segment-and-Track-Anything-main/sam/segment_anything/automatic_mask_generator.py", line 163, in generate
    mask_data = self._generate_masks(image)
  File "/home/gcbm/workspace/Segment-and-Track-Anything-main/sam/segment_anything/automatic_mask_generator.py", line 212, in _generate_masks
    scores = 1 / box_area(data["crop_boxes"])
  File "/home/gcbm/workspace/anaconda3/envs/track/lib/python3.9/site-packages/torchvision/ops/boxes.py", line 235, in box_area
    return (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
IndexError: too many indices for tensor of dimension 1

Is this a version issue? I didn't find a solution

[Bentonmaster]

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
Cell In[3], line 20
     18 ret, frame = cap.read()
     19 frame = cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
---> 20 pred_mask = segtracker.seg(frame)
     21 torch.cuda.empty_cache()
     22 obj_ids = np.unique(pred_mask)

File ~/workspace/Segment-and-Track-Anything-main/SegTracker.py:45, in SegTracker.seg(self, frame)
     38 '''
     39 Arguments:
     40     frame: numpy array (h,w,3)
     41 Return:
     42     origin_merged_mask: numpy array (h,w)
     43 '''
     44 frame = frame[:, :, ::-1]
---> 45 anns = self.sam.everything_generator.generate(frame)
     47 # anns is a list recording all predictions in an image
     48 if len(anns) == 0:

File ~/workspace/anaconda3/envs/track/lib/python3.9/site-packages/torch/utils/_contextlib.py:115, in context_decorator.<locals>.decorate_context(*args, **kwargs)
    112 @functools.wraps(func)
    113 def decorate_context(*args, **kwargs):
    114     with ctx_factory():
--> 115         return func(*args, **kwargs)

File ~/workspace/Segment-and-Track-Anything-main/sam/segment_anything/automatic_mask_generator.py:163, in SamAutomaticMaskGenerator.generate(self, image)
    138 """
    139 Generates masks for the given image.
    140 
   (...)
    159          the mask, given in XYWH format.
    160 """
    162 # Generate masks
--> 163 mask_data = self._generate_masks(image)
    165 # Filter small disconnected regions and holes in masks
    166 if self.min_mask_region_area > 0:

File ~/workspace/Segment-and-Track-Anything-main/sam/segment_anything/automatic_mask_generator.py:212, in SamAutomaticMaskGenerator._generate_masks(self, image)
    209 # Remove duplicate masks between crops
    210 if len(crop_boxes) > 1:
    211     # Prefer masks from smaller crops
--> 212     scores = 1 / box_area(data["crop_boxes"])
    213     scores = scores.to(data["boxes"].device)
    214     keep_by_nms = batched_nms(
    215         data["boxes"].float(),
    216         scores,
    217         torch.zeros(len(data["boxes"])),  # categories
    218         iou_threshold=self.crop_nms_thresh,
    219     )

File ~/workspace/anaconda3/envs/track/lib/python3.9/site-packages/torchvision/ops/boxes.py:235, in box_area(boxes)
    233     _log_api_usage_once(box_area)
    234 boxes = _upcast(boxes)
--> 235 return (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])

IndexError: too many indices for tensor of dimension 1

When I run demo. ipynb，The same error occurred