Error about custom data training

[ansebby]

I met error as below when I try to train the custom data(512*512 jpg images). What is the problem? Please review my error message.

python3 train.py --model_def config/yolov3-custom.cfg --data_config config/custom.data --img_size 64

Namespace(batch_size=8, checkpoint_interval=1, compute_map=False, data_config='config/custom.data', epochs=100, evaluation_interval=1, gradient_accumulations=2, img_size=64, model_def='config /yolov3-custom.cfg', multiscale_training=True, n_cpu=8, pretrained_weights=None) Traceback (most recent call last): File "train.py", line 100, in for batch_i, (_, imgs, targets) in enumerate(dataloader): File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in next return self._process_data(data) File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/opt/anaconda3/lib/python3.7/site-packages/torch/_utils.py", line 385, in reraise raise self.exc_type(msg) TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/opt/anaconda3/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 "/opt/anaconda3/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/ansebby/PyTorch-YOLOv3/utils/datasets.py", line 130, in getitem img, targets = horisontal_flip(img, targets) File "/home/ansebby/PyTorch-YOLOv3/utils/augmentations.py", line 8, in horisontal_flip targets[:, 2] = 1 - targets[:, 2] TypeError: 'NoneType' object is not subscriptable

[jchhuang]

Have you solve this problem，I meet the same as you

[ansebby]

Not yet. How about you?

2020년 1월 24일 (금) 오전 12:04, jchhuang [email protected]님이 작성:

Have you solve this problem，I meet the same as you

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/eriklindernoren/PyTorch-YOLOv3/issues/402?email_source=notifications&email_token=AGIA4TIBQD7HV2QZO7DERVLQ7GWZFA5CNFSM4KDD2UHKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEJXVD5I#issuecomment-577720821, or unsubscribe https://github.com/notifications/unsubscribe-auth/AGIA4TOTCAHBNLZEZOBHD5TQ7GWZFANCNFSM4KDD2UHA .

[jzr0065]

check the names of your images to see whether it end with '.jpg' or '.png', lowercase and uppercase make difference.

[guancheng817]

check the names of your images to see whether it end with '.jpg' or '.png', lowercase and uppercase make difference.

my dataset ends with 'png' and still appear the error, how should I modify?Thanks

[tienthegainz]

Modify this line:

path.lower().replace("images", "labels").replace(
                ".png", ".txt").replace(".jpg", ".txt").replace(".jpeg", ".txt").replace(".jpeg", ".txt")

[summeryumyee]

mark

[Flova]

Is this issue still relevant/occurring?