I want to be able to save the state of training my neural net using SGD. I know I can save the weights using the save_weights function. What I don't know is how to save the momentum of the gradient decent. Does anyone know how to do this?
使用model.optimizer.get_state()
和model.optimizer.set_state()
- 请参阅https://github.com/fchollet/keras/issues/454 。
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.