Replies: 1 comment
-
Hi, @boundaryT. Please follow these instructions to open an issue with detailed information on your problem. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
for i,file in enumerate(input_files): print("data_process" + str(i)) print(file) subject = tio.Subject(source=tio.data.ScalarImage(file)) grid_sampler = tio.inference.GridSampler( subject, # some NumPy array patch_size=(88, 88, 60), patch_overlap=4, ) tio.data.inference.aggregator patch_loader = torch.utils.data.DataLoader(grid_sampler, batch_size=4) print(grid_sampler.subject) aggregator = tio.inference.GridAggregator(grid_sampler) print(aggregator.patch_overlap) with torch.no_grad(): for patches_batch in patch_loader: print(1111111111) input_tensor = patches_batch['source'][tio.DATA] #test --not enter model print(input_tensor) locations = patches_batch[tio.LOCATION] logging.info("OK") aggregator.add_batch(input_tensor, locations) output_tensor = aggregator.get_output_tensor()
Beta Was this translation helpful? Give feedback.
All reactions