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

很不错的repo #8

Open
myzhuang opened this issue Mar 27, 2021 · 0 comments
Open

很不错的repo #8

myzhuang opened this issue Mar 27, 2021 · 0 comments

Comments

@myzhuang
Copy link

很不错的repo,展示了不同模型优化技术的作用。
最近也是在跑CIFAR10的任务,不过用的是pytorch。
然后我的疑问是resnet系列的准确率是不是偏低一点?理论上resnet系列的准确率应该比VGG16好好一点的。
我这边跑的VGG16 的准确率可以到达93.49%,超过了你展示的resnet结果。我在想是不是resnet全部潜能没有发挥出来?
我的实验设置如下:
结构是官方VGG16,有加BN,Batch大小500,fc加dropout
SGD,余弦学习率,lr初始值0.1,半衰周期1200,最小学习率0.001。
权重衰减5e-4
输入图像padding再随机裁剪4像素,没有做白化。加水平镜像翻转

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

1 participant