When I run python run_tree_ring_watermark.py --run_name jpeg --w_channel 3 --w_pattern ring --jpeg_ratio 25 --start 0 --end 1000 --with_tracking,I encounter the following issue at 315/1000,What should I do?
Traceback (most recent call last):
File "run_tree_ring_watermark.py", line 221, in
main(args)
File "run_tree_ring_watermark.py", line 107, in main
img_no_w = transform_img(orig_image_no_w_auged).unsqueeze(0).to(text_embeddings.dtype).to(device)
File "/root/autodl-tmp/tree-ring-watermark-main/optim_utils.py", line 37, in transform_img
image = tform(image)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 95, in call
img = t(img)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 361, in forward
return F.resize(img, self.size, self.interpolation, self.max_size, self.antialias)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/functional.py", line 490, in resize
return F_pil.resize(img, size=output_size, interpolation=pil_interpolation)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/_functional_pil.py", line 250, in resize
return img.resize(tuple(size[::-1]), interpolation)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/PIL/Image.py", line 2293, in resize
self.load()
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/PIL/ImageFile.py", line 312, in load
raise _get_oserror(err_code, encoder=False)
OSError: broken data stream when reading image file
When I run python run_tree_ring_watermark.py --run_name jpeg --w_channel 3 --w_pattern ring --jpeg_ratio 25 --start 0 --end 1000 --with_tracking,I encounter the following issue at 315/1000,What should I do? Traceback (most recent call last): File "run_tree_ring_watermark.py", line 221, in
main(args)
File "run_tree_ring_watermark.py", line 107, in main
img_no_w = transform_img(orig_image_no_w_auged).unsqueeze(0).to(text_embeddings.dtype).to(device)
File "/root/autodl-tmp/tree-ring-watermark-main/optim_utils.py", line 37, in transform_img
image = tform(image)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 95, in call
img = t(img)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 361, in forward
return F.resize(img, self.size, self.interpolation, self.max_size, self.antialias)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/functional.py", line 490, in resize
return F_pil.resize(img, size=output_size, interpolation=pil_interpolation)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/torchvision/transforms/_functional_pil.py", line 250, in resize
return img.resize(tuple(size[::-1]), interpolation)
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/PIL/Image.py", line 2293, in resize
self.load()
File "/root/miniconda3/envs/tree-ring/lib/python3.8/site-packages/PIL/ImageFile.py", line 312, in load
raise _get_oserror(err_code, encoder=False)
OSError: broken data stream when reading image file