This is a simple VGG16 net implemented in CUDA.
Simply run make; ./a.out to test the code. You may need to setup the environment for CUDA, cudnn, cublas.
The convolution layers use cudnn, and the FC layer uses cublas.
-
Notifications
You must be signed in to change notification settings - Fork 1
tigercosmos/simple-vgg16-cu
About
Simple VGG16 implemented in CUDA
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published