-
Notifications
You must be signed in to change notification settings - Fork 207
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
训练速度过慢的问题? #14
Comments
(I am not among the authors. Just for discussion.) I think this could be normal. One possible reason is that the data is not real. The information per sample can be limited, so basically the student network needs to see many more samples than the training on real data. |
But I think this speed is unacceptable in actual use. Moreover, only small data sets are used in the experiment. If semantic segmentation, imagenet, and high-resolution images tasks are used, the computational complexity is very large. It is estimated that GAN cannot reasonably infer the distribution equivalent to real data. |
欢迎star我的仓库一起交流KD:https://github.com/FLHonker/Awesome-Knowledge-Distillation |
Yeah, you've made a point. ImageNet would be substantially harder. It definitely has a long road before practical use. But Rome is not built in one day. I think this paper can be a good start. |
我也一直试图改进这个问题,除非抛弃GAN,GAN的训练是个痛点。data-free是个很有意思的topic。 |
Thanks for MingSun-Tse's answer. That's right. We will develop a more efficient data-free learning method in the future work. |
MNIST从原本的10epcoh在DAFL框架下要训练200epoch,CIFAR-10要训练2000epoch。而且GAN的训练也耗时,经过实验比标准KD训练时间长了20-30倍。
The text was updated successfully, but these errors were encountered: