More than one bounding box

[sulaimanvesal]

Hi all,

When I use more than one bounding box, I get the following errors. I checked everything the shape of bboxs are BxNx4.

Draw bounding boxes on the image and press 'q' when done.
Bounding box added: [522, 622, 662, 752]
Bounding box added: [742, 713, 871, 832]
User-Drawn Bounding Boxes: [[522 622 662 752]
 [742 713 871 832]] (2, 4)
Traceback (most recent call last):
  File "D:\Hanwha_Projects\Project2\DPM_MobileSAm\run_demo_ultralytics.py", line 70, in <module>
    masks_object, _, _ = model.predict(
  File "d:\hanwha_projects\project2\dpm_mobilesam\mobilesam\mobile_sam\predictor.py", line 155, in predict
    masks, iou_predictions, low_res_masks = self.predict_torch(
  File "C:\ProgramData\anaconda3\envs\pytorch_env\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "d:\hanwha_projects\project2\dpm_mobilesam\mobilesam\mobile_sam\predictor.py", line 223, in predict_torch
    sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
  File "C:\ProgramData\anaconda3\envs\pytorch_env\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "d:\hanwha_projects\project2\dpm_mobilesam\mobilesam\mobile_sam\modeling\prompt_encoder.py", line 159, in forward
    sparse_embeddings = torch.cat([sparse_embeddings, box_embeddings], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.