Skip to content
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.

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

训练问题 #85

Open
jing941 opened this issue Apr 11, 2022 · 4 comments
Open

训练问题 #85

jing941 opened this issue Apr 11, 2022 · 4 comments

Comments

@jing941
Copy link

jing941 commented Apr 11, 2022

你好,我单独使用coco数据集进行训练,出现如下错误是什么原因
Traceback (most recent call last):
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/tools/train.py", line 315, in
main()
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/tools/train.py", line 288, in main
train_loader = build_data_loader()
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/tools/train.py", line 61, in build_data_loader
train_dataset = TrkDataset()
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/pysot/datasets/dataset.py", line 159, in init
start
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/pysot/datasets/dataset.py", line 44, in init
meta_data = self._filter_zero(meta_data)
File "/home/s/ymt/Siam-car/yuanCAR/SiamCAR-master/pysot/datasets/dataset.py", line 76, in _filter_zero
for frm, bbox in frames.items():
AttributeError: 'str' object has no attribute 'items'
期待您的回信,谢谢!

@sai-fu
Copy link

sai-fu commented May 9, 2022

should convert data type

@sai-fu
Copy link

sai-fu commented May 9, 2022

hello ,I use the got10k dataset to train alone, and the following error occurs
File "D:\parcharm_pro\SiamCAR-master\pysot\utils\model_load.py", line 59, in load_pretrain
check_keys(model, pretrained_dict)
File "D:\parcharm_pro\SiamCAR-master\pysot\utils\model_load.py", line 35, in check_keys
'load NONE from pretrained checkpoint'
AssertionError: load NONE from pretrained checkpoint

@jing941
Copy link
Author

jing941 commented May 12, 2022

Maybe the path to the pre-trained model could not be found

@chenxlin222
Copy link

您好,请问如果单独用got-10k数据集训练的话,__C.DATASET.GOT.NUM_USE (100000), __C.DATASET.VIDEOS_PER_EPOCH (600000),还有__C.TRAIN.EPOCH (20),这些参数有改变吗?应该改成多少比较合适呢?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants