New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

KeyError: 12 when training #754

Closed

yao-zheng-yi opened this issue Jun 20, 2020 · 4 comments

yao-zheng-yi commented Jun 20, 2020

anyone can help me？

ctdet/yxh |### | train: [1][1152/11176]|Tot: 0:03:32 |ETA: 0:31:52 |loss 7.0469 |hm_loss 5.6721 |wh_loss 11.1695 |off_loss 0.2578 |Dat
ctdet/yxh |### | train: [1][1153/11176]|Tot: 0:03:32 |ETA: 0:31:52 |loss 7.0438 |hm_loss 5.6696 |wh_loss 11.1645 |off_loss 0.2578 |Dat
ctdet/yxh |### | train: [1][1154/11176]|Tot: 0:03:33 |ETA: 0:31:52 |loss 7.0415 |hm_loss 5.6676 |wh_loss 11.1610 |off_loss 0.2578 |Dat
ctdet/yxh |### | train: [1][1155/11176]|Tot: 0:03:33 |ETA: 0:31:52 |loss 7.0397 |hm_loss 5.6666 |wh_loss 11.1537 |off_loss 0.2578 |Dat
ctdet/yxh |### | train: [1][1156/11176]|Tot: 0:03:33 |ETA: 0:28:37 |loss 7.0365 |hm_loss 5.6640 |wh_loss 11.1480 |off_loss 0.2578 |Dat
ctdet/yxh |### | train: [1][1157/11176]|Tot: 0:03:33 |ETA: 0:28:37 |loss 7.0330 |hm_loss 5.6611 |wh_loss 11.1411 |off_loss 0.2578 |Data 0.002s(0.002s) |Net 0.185sTraceback (most recent call last):
File "main.py", line 102, in
main(opt)
File "main.py", line 70, in main
log_dict_train, _ = trainer.train(epoch, train_loader)
File "/home/cwy/CenterNet-master/src/lib/trains/base_trainer.py", line 119, in train
return self.run_epoch('train', epoch, data_loader)
File "/home/cwy/CenterNet-master/src/lib/trains/base_trainer.py", line 61, in run_epoch
for iter_id, batch in enumerate(data_loader):
File "/home/cwy/.conda/envs/yolo/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 568, in next
return self._process_next_batch(batch)
File "/home/cwy/.conda/envs/yolo/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 606, in _process_next_batch
raise Exception("KeyError:" + batch.exc_msg)
Exception: KeyError:Traceback (most recent call last):
File "/home/cwy/.conda/envs/yolo/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/cwy/.conda/envs/yolo/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/cwy/CenterNet-master/src/lib/datasets/sample/ctdet.py", line 102, in getitem
cls_id = int(self.cat_ids[ann['category_id']])
KeyError: 12

Author

yao-zheng-yi commented Jun 21, 2020

I guess the problem maybe in train.json，but I can‘t find error.
感觉是json文件的问题，但是有时候又可以正常训练，报错信息太少了不知道怎么找原因，到底是哪里出错了呢？

Author

yao-zheng-yi commented Jun 22, 2020

我知道了，类别ID的列表少了个12，低级错误

yao-zheng-yi closed this as completed

wwq98 commented Oct 25, 2020

你好请问怎么解决呢？

wwq98 commented Oct 25, 2020

解决了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment