Sorry But I don't know what exactly mean 'delete the checkpoint directory to train a new model'

[eastsky0614]

Hello, I study Face Recognition and I'm interested in your paper.

First of all, Thank you for sharing your code. I want to train your model with my own dataset. I find your answer about same question, But I could not understand 'delete the checkpoint directory'.

I already try to delete checkpoint folder in dcgan-completion.tensorflow and delete the checkpoint text file or all files in the checkpoint folder. But, It doesn't work.

Could you let me know more information to train a new dataset?

Thank you and Hope you have a nice day. Bye

[qiuxiaqing]

I meet the same problem. How do you solve this problem？