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

How to train without the pre-trained cornernet model #8

Closed
XiaoR666 opened this issue Mar 2, 2019 · 2 comments
Closed

How to train without the pre-trained cornernet model #8

XiaoR666 opened this issue Mar 2, 2019 · 2 comments

Comments

@XiaoR666
Copy link

XiaoR666 commented Mar 2, 2019

thank u for your code very much,i don not want to fine-tun from the cornernet model and how to train the model from scratch

@xingyizhou
Copy link
Owner

Hi,
Thanks for your interests. You can delete this line https://github.com/xingyizhou/ExtremeNet/blob/master/config/ExtremeNet.json#L26 to train from scratch. To fully reproduce our results, you will also need to increase the training iterations https://github.com/xingyizhou/ExtremeNet/blob/master/config/ExtremeNet.json#L18 . We have tried "max_iter": 500000, "stepsize": 450000, it works slightly better than fine-tuning CornerNet. Our model is given at https://drive.google.com/file/d/1omiOUjWCrFbTJREypuZaODu0bOlF_7Fg/view?usp=sharing .

@XiaoR666
Copy link
Author

XiaoR666 commented Mar 5, 2019

Thanks very much,it help me a lot.

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

2 participants