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 my own data? #12

Closed
zcc720 opened this issue Jun 7, 2018 · 4 comments
Closed

how to train my own data? #12

zcc720 opened this issue Jun 7, 2018 · 4 comments

Comments

@zcc720
Copy link

zcc720 commented Jun 7, 2018

1.can this project train my own data?
2.if can,how to train?

@HiKapok
Copy link
Owner

HiKapok commented Jun 7, 2018

Yes, of course. please follow dataset/convert_tfrecords.py to make your own *.tfrecords for your own dataset

@moonyoung430
Copy link

I want to train my own data too, and I already make my own *.tfrecords. But when I run train_ssd.py ,I found that must provide the checkpoint_path,the path to a checkpoint from which to fine-tune,and put the pre-trained VGG-16 model in it. my question is pre-trained VGG-16 is not sutable for my dataset. How to solve it?

@moonyoung430
Copy link

@HiKapok

@HiKapok
Copy link
Owner

HiKapok commented Jun 7, 2018

@moonyoung430 set scafford to None if you don't want use a pretained weights

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