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

KeyError: 'pytorch-lightning_version' #137

Open
laster-lee opened this issue Apr 25, 2024 · 4 comments
Open

KeyError: 'pytorch-lightning_version' #137

laster-lee opened this issue Apr 25, 2024 · 4 comments

Comments

@laster-lee
Copy link

laster-lee commented Apr 25, 2024

Traceback (most recent call last):
File "e:\kc_infer\kc_test.py", line 7, in
parseq = load_from_checkpoint("./parseq_tiny.pt").eval()
File "e:\kc_infer\strhub\models\utils.py", line 92, in load_from_checkpoint
model = ModelClass.load_from_checkpoint(checkpoint_path, **kwargs)
File "D:\anaconda3\envs\kc_infer\lib\site-packages\pytorch_lightning\utilities\model_helpers.py", line 125, in wrapper
return self.method(cls, *args, **kwargs)
File "D:\anaconda3\envs\kc_infer\lib\site-packages\pytorch_lightning\core\module.py", line 1581, in load_from_checkpoint
loaded = _load_from_checkpoint(
File "D:\anaconda3\envs\kc_infer\lib\site-packages\pytorch_lightning\core\saving.py", line 66, in _load_from_checkpoint
checkpoint = _pl_migrate_checkpoint(
File "D:\anaconda3\envs\kc_infer\lib\site-packages\pytorch_lightning\utilities\migration\utils.py", line 143, in _pl_migrate_checkpoint
old_version = _get_version(checkpoint)
File "D:\anaconda3\envs\kc_infer\lib\site-packages\pytorch_lightning\utilities\migration\utils.py", line 164, in _get_version
return checkpoint["pytorch-lightning_version"]
KeyError: 'pytorch-lightning_version'

@EtherealTan
Copy link

i have the same question have you solved it?

@laster-lee
Copy link
Author

i have the same question have you solved it?我有同样的问题,你解决了吗?

没解决,后面我自己训练模型了,用自己的数据集

@GIN-Margarita
Copy link

you need execuate with --checkpoint pretrained=<model_name>

example:
python read.py --checkpoint pretrained=vitstr --images ./demo_images/art-01107.jpg ./demo_images/coco-1166773.jpg
meanwhile ,you need update read.py args with --checkpoints , such as :
image

@GIN-Margarita
Copy link

additionally , utils.py has urls of model
you could update url with the local dir.
image

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