Skip to content
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

有试过用tensorflow的模型跑一跑么? #4

Open
msnh2012 opened this issue Apr 14, 2020 · 7 comments
Open

有试过用tensorflow的模型跑一跑么? #4

msnh2012 opened this issue Apr 14, 2020 · 7 comments

Comments

@msnh2012
Copy link

如上。

@yizt
Copy link
Owner

yizt commented Apr 14, 2020 via email

@msnh2012
Copy link
Author

用numpy重构下一些基础网络,然后加载tensorflow pb数据,进行前向运算

@yizt
Copy link
Owner

yizt commented Apr 15, 2020

@msnh2012 没有测试过,请问tensorflow pb的数据指定是mnist,cifar还是其它的?

@msnh2012
Copy link
Author

都行呀,比如构建个VGG16试试,看可行不可行。

@yizt
Copy link
Owner

yizt commented Apr 15, 2020

@msnh2012 纯numpy,估计速度很慢,所有没有没有弄很多层;不过,你提的是个好建议,周末测试一下vgg16看看,有结果,给你消息哈

@yizt
Copy link
Owner

yizt commented May 10, 2020

@msnh2012 用vgg11在cifar10上测试验证了下;当然速度是很慢很慢的,batch-size为32,训练一个step大概1分钟;训练1w步后,模型在测试集上精度为0.576;详见3_1-VGG.md

@msnh2012
Copy link
Author

可能训练是不太理想,inference应该还行

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants