PyTorch-YOLOv3
PyTorch-YOLOv3 copied to clipboard
Error about custom data training
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
Have you solve this problem,I meet the same as you
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 .
check the names of your images to see whether it end with '.jpg' or '.png', lowercase and uppercase make difference.
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
Modify this line:
path.lower().replace("images", "labels").replace(
".png", ".txt").replace(".jpg", ".txt").replace(".jpeg", ".txt").replace(".jpeg", ".txt")
mark
Is this issue still relevant/occurring?