This is re-implementation Wide-ResNet in Caffe. I have run this code on CIFAR-10, and got an average accuracy of 96.05, even better than the rasult in paper. This WRN-28 model do not use any dropout layer. This model was trained on 4 way GTX1080Ti.
-
Notifications
You must be signed in to change notification settings - Fork 1
baoachun/Wide-ResNet_Caffe
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
This is re-implementation Wide-ResNet in Caffe
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published