File "mmocr_sam_erase.py", line 269, in
masks, _, _ = sam_predictor.predict_torch(
File "/opt/conda/envs/ocr-sam/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/opt/conda/envs/ocr-sam/lib/python3.8/site-packages/segment_anything/predictor.py", line 229, in predict_torch
low_res_masks, iou_predictions = self.model.mask_decoder(
File "/opt/conda/envs/ocr-sam/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/envs/ocr-sam/lib/python3.8/site-packages/segment_anything/modeling/mask_decoder.py", line 94, in forward
masks, iou_pred = self.predict_masks(
File "/opt/conda/envs/ocr-sam/lib/python3.8/site-packages/segment_anything/modeling/mask_decoder.py", line 144, in predict_masks
masks = (hyper_in @ upscaled_embedding.view(b, c, h * w)).view(b, -1, h, w)
RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1, 256, 256] because the unspecified dimension size -1 can be any value and is ambiguous
I also encountered this problem, have you solved it?
yeungchenwa
