SherlockHolmes221
commented
2 years ago it is correct, will fix it soon
Closed xz-123-new closed 2 years ago
SherlockHolmes221
commented
2 years ago it is correct, will fix it soon
I tried to train the model on hicodet dataset, but there was a problem, and the error message was as follows: Traceback (most recent call last): File "/home/xuzhu/DOQ/main.py", line 322, in
main(args)
File "/home/xuzhu/DOQ/main.py", line 267, in main
train_stats = train_one_epoch(
File "/home/xuzhu/DOQ/engine.py", line 43, in train_one_epoch
for samples, targets in metric_logger.log_every(data_loader, print_freq, header):
File "/home/xuzhu/DOQ/util/misc.py", line 228, in log_every
for obj in iterable:
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1065, in _next_data
return self._process_data(data)
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
Exception: Caught Exception in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/xuzhu/anaconda3/envs/qpic/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/xuzhu/DOQ/datasets/hico.py", line 65, in getitem
img_anno, img = get_replace_image(random_index, self.annotations, self.img_folder, "hoia")
File "/home/xuzhu/DOQ/datasets/stitch_images.py", line 462, in get_replace_image
raise Exception('not support dateset')
Exception: not support dateset
But when I change the code ‘img_anno, img = get_replace_image(random_index, self.annotations, self.img_folder, "hoia")’ into 'img_anno, img = get_replace_image(random_index, self.annotations, self.img_folder, "hico")',i.e. change dataset_file from hoia to hico,it could train as normal,i'm not sure if i was doing the correct thing,could you please explain it to me.Looking foward to your reply,thanks!