-
Notifications
You must be signed in to change notification settings - Fork 11
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
Other networks #4
Comments
Yes, it can be applied to other networks. Line 361 here is not to emphasize the version of Resnet "18". The batchnorm function is used in the BasicBlock/Bottleneck which are used by different versions of ResNet. If you read the source code of ResNet carefully, you won't have such questions. Well, actually you need to modify some details if you use other networks. I believe you can find these places to modify by debugging. |
Have you ever try your method on resnet18 or resnet50? |
I have tried some different versions of ResNet on VD instead of PACS, and see some slight improvement with more layers of ResNet.
… 在 2019年11月3日,下午5:41,keyu07 ***@***.***> 写道:
Have you ever try your method on resnet18 or resnet50?
How is the performance?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
Can this code apply to other pretrained networks? like resnet18, resnet50.
Based on the line 361 in model_PACS, it seems it cannot apply on resnet18.
I have tried resnet50, but there are many details need to be modified.
The text was updated successfully, but these errors were encountered: