I'll ask you questions about some errors!

[choikhss]

HI! I have several questions, so i will ask by number.!!

-1-
Traceback (most recent call last):
File "src/train_core.py", line 124, in
trainer.train(epoch)
File "./trainers/coretrainer.py", line 36, in train
for i_batch, batch in enumerate(self.train_loader):
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in next
return self._process_data(data)
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
data.reraise()
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise
raise self.exc_type(msg)
cv2.error: Caught error in DataLoader worker process 0.

-2-
Original Traceback (most recent call last):
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/user/anaconda3/envs/hybridpose/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/user/PycharmProjects/hybridpose/HybridPose/lib/datasets/concat.py", line 48, in getitem
return self.datasets[dataset_idx][sample_idx, height, width]
File "/home/user/PycharmProjects/hybridpose/HybridPose/lib/datasets/blender_linemod.py", line 204, in getitem
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
cv2.error: OpenCV(3.4.7) ../modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

-3-
When i run 'train_core', <model = nn.DataParallel(model).cuda()> code is too slow :(
It takes about 15 minutes..or more ..

--
All of these Problems occur When running train_core code !

I'll wait for your reply!
Thank you!

[chensong1995]

Hello choikhss,

Thanks for the interest in our work! Please make sure you have correctly prepared the datasets according to README.

I hope this helps.