facebookresearch / facebookresearch/segment-anything
RuntimeError: Could not infer dtype of numpy.uint8
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
I would appreciate it if you could assist me with how to fix the error below.
`---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Cell In[26], line 2
1 #image = torch.as_tensor(image, device=device, dtype=torch.uint8)
----> 2 predictor.set_image(image)
File ~\AppData\Local\anaconda3\envs\dev\lib\site-packages\segment_anything\predictor.py:57, in SamPredictor.set_image(self, image, image_format)
55 # Transform the image to the form expected by the model
56 input_image = self.transform.apply_image(image)
---> 57 input_image_torch = torch.as_tensor(input_image, device=self.device)
58 input_image_torch = input_image_torch.permute(2, 0, 1).contiguous()[None, :, :, :]
60 self.set_torch_image(input_image_torch, image.shape[:2])
RuntimeError: Could not infer dtype of numpy.uint8`
Contributor guide
Assessment
This issue has not been assessed yet.