pytorch/examples

Gradient vanishing of G in the DCGAN example

Open

#822 创建于 2020年9月11日

在 GitHub 查看
 (0 评论) (0 反应) (0 负责人)Python (21,634 star) (9,429 fork)batch import
help wanted

描述

Hello,

I have trained the DCGAN with the default hyper-parameter settings on the downloaded "img_align_celeba" dataset (recommended in the tutorial). However, the results reveal strong gradient vanishing of G. While Loss_D keeps decreasing towards 0, Loss_G grows high (towards 100).

It seems that D is trained so well, preventing a good training on G. I didn't do any modifications on the code. Do you know what happened?

Thanks!

贡献者指南

技术栈
python
领域
machine learning
议题类型
research
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
needs investigation
前置要求
Understanding of GANsFamiliarity with PyTorchBasic knowledge of DCGAN
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
Investigate the default hyperparameters in the DCGAN example. Check the learning rates for generator and discriminator, and consider adjusting them. Look at the loss function implementation to ensure it matches the original DCGAN paper. Additionally, try using different GAN training techniques like label smoothing or adding noise to the discriminator inputs.