How to fix following error (using given sample code)

[terrencechungong]

---

RuntimeError Traceback (most recent call last)
Cell In[5], line 12
9 image = Image.open(img_path)
10 mask = Image.open(mask_path).convert('L')
---> 12 result = simple_lama(image, mask)
13 result.save("inpainted.png")

File /scratch0/tchungon/anaconda3/envs/samxlama/lib/python3.8/site-packages/simple_lama_inpainting/models/model.py:32, in SimpleLama.call(self, image, mask)
29 image, mask = prepare_img_and_mask(image, mask, self.device)
31 with torch.inference_mode():
---> 32 inpainted = self.model(image, mask)
34 cur_res = inpainted[0].permute(1, 2, 0).detach().cpu().numpy()
35 cur_res = np.clip(cur_res * 255, 0, 255).astype(np.uint8)

File /scratch0/tchungon/anaconda3/envs/samxlama/lib/python3.8/site-packages/torch/nn/modules/module.py:1511, in Module._wrapped_call_impl(self, *args, **kwargs)
1509 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1510 else:
-> 1511 return self._call_impl(*args, **kwargs)

File /scratch0/tchungon/anaconda3/envs/samxlama/lib/python3.8/site-packages/torch/nn/modules/module.py:1520, in Module._call_impl(self, *args, **kwargs)
1515 # If we don't have any hooks, we want to skip the rest of the logic in
1516 # this function, and just call forward.
1517 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1518 or _global_backward_pre_hooks or _global_backward_hooks
...
/home/enesmsahin/.conda/envs/sdiff/lib/python3.9/site-packages/hydra/_internal/utils.py(367): _run_hydra
/home/enesmsahin/.conda/envs/sdiff/lib/python3.9/site-packages/hydra/main.py(49): decorated_main
/home/enesmsahin/enes_workspace/lama/bin/to_jit.py(78):
RuntimeError: Given groups=1, weight of size [64, 4, 7, 7], expected input[1, 5, 1054, 2462] to have 4 channels, but got 5 channels instead
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

[insanebai]

You need to modify the given sample code：

from simple_lama_inpainting import SimpleLama
from PIL import Image

simple_lama = SimpleLama()

img_path = "image.png"
mask_path = "mask.png"

image = Image.open(img_path).convert('RGB')
mask = Image.open(mask_path).convert('L')

result = simple_lama(image, mask)
result.save("inpainted.png")

Because the default mode of PIL package is "ARGB" and its channels are 4.