[cuda-pool]: an demo of device pooling layer

fengggli / gpu-computing-materials

A simple deep learning framework that optimizes task scheduling and memory usage on different CPU/GPU architectures.

1 stars 0 forks source link

Closed fengggli closed 5 years ago

fengggli commented 5 years ago

use cmake -DUSE_CUDA=on .. to build cuda pool layer, by default it's turned off.
checked both forward/backward of the device pooling.
Added missing test_solver file