SunnyHaze
commented
3 months ago Hi, thanks for your attention to our work.
As stated in the error stack, the sizes of the tampered image and the ground truth image in the provided dataset do not match. The following solutions might help you resolve this issue:
If you are using mani_dataset to read the dataset, consider whether the images and masks in the /Tp and /Gt folders have matching names, or at least have the same order when sorted.
If that is not the issue, consider whether the corresponding images and masks have inconsistent sizes. You can set this variable to True to check the specific filenames: link to the variable.
Hope this helps you, if you have further issue, feel free to reach out.
hcztxdy
fangfangbuaibiancheng
Hello, I had a problem with the mismatch between the TP and GT sizes while training, but the GT is not at all 800x518 in size, do you know what's going on Traceback (most recent call last): File "main_train.py", line 269, in
main(args)
File "main_train.py", line 220, in main
args=args
File "/opt/data/private/LL/IML-ViT-main/engine_train.py", line 37, in train_one_epoch
for data_iter_step, (samples, masks, edge_mask, shape) in enumerate(metric_logger.log_every(data_loader, print_freq, header)):
File "/opt/data/private/LL/IML-ViT-main/utils/misc.py", line 146, in log_every
for obj in iterable:
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 628, in next
data = self._next_data()
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
return self._process_data(data)
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
data.reraise()
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/_utils.py", line 543, in reraise
raise exception
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch(index)
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/anaconda3/envs/pytorch-LL/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/data/private/LL/IML-ViT-main/utils/datasets.py", line 88, in getitem
assert tp_shape == gt_shape, "tp and gt image shape must be the same, but got {} and {}".format(tp_shape, gt_shape)
AssertionError: tp and gt image shape must be the same, but got (256, 384) and (800, 518)