images = torch.cat([x[0][None] for x in items], dim=0)

[baoyuchen]

------------------------------------------Start training-------------------------------------------
## Using Self-defined Scheduler-flatcosine ##
[0.0004, 0.0004, 0.0008, 0.0008] [0.0004, 0.0004, 0.0008, 0.0008] 11200 2000 546000 840
number of trainable parameters: 3731815
<class 'list'>
Traceback (most recent call last):
File "H:\DEELABWORKPLACE\DEIM-main\train.py", line 82, in
main(args)
File "H:\DEELABWORKPLACE\DEIM-main\train.py", line 52, in main
solver.fit()
File "H:\DEELABWORKPLACE\DEIM-main\engine\solver\det_solver.py", line 76, in fit
train_stats = train_one_epoch(
File "H:\DEELABWORKPLACE\DEIM-main\engine\solver\det_engine.py", line 42, in train_one_epoch
for i, (samples, targets) in enumerate(metric_logger.log_every(data_loader, print_freq, header)):
File "H:\DEELABWORKPLACE\DEIM-main\engine\misc\logger.py", line 215, in log_every
for obj in iterable:
File "E:\software\miniconda\envs\mydeim\lib\site-packages\torch\utils\data\dataloader.py", line 631, in next
data = self._next_data()
File "E:\software\miniconda\envs\mydeim\lib\site-packages\torch\utils\data\dataloader.py", line 675, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "E:\software\miniconda\envs\mydeim\lib\site-packages\torch\utils\data_utils\fetch.py", line 54, in fetch
return self.collate_fn(data)
File "H:\DEELABWORKPLACE\DEIM-main\engine\data\dataloader.py", line 183, in call
images = torch.cat([x[0][None] for x in items], dim=0)
File "H:\DEELABWORKPLACE\DEIM-main\engine\data\dataloader.py", line 183, in
images = torch.cat([x[0][None] for x in items], dim=0)
TypeError: 'Image' object is not subscriptable
(mydeim) PS H:\DEELABWORKPLACE\DEIM-main>

[ShihuaHuang95]

Thank you very much for your interest in and attention to our work.
Your issue seems to be caused by a mismatch in your dataset, which prevents it from being loaded correctly. We suggest diving into the Dataloader to further debug this problem.