The learning rate does not decline

MaybeShewill-CV / attentive-gan-derainnet

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

MIT License

262 stars 83 forks source link

The learning rate does not decline #27

Closed WilyZhao8 closed 5 years ago

WilyZhao8 commented 5 years ago

I use this project to train my own data, and found that the learning_rata does not decline, It was always a fixed value(0.0002).

MaybeShewill-CV commented 5 years ago

@WilyZhao8 The lr decay follows the exponential_decay. You may check the code:)