weiyichang

Moreover, does OpenGL backend supports FC layers and Element-wise layer ?

Hi, I encounter the same problem about running googlenet (download from https://github.com/caffe2/models/tree/master/bvlc_googlenet) on Android phone. Does anyone solve this problem? or Any suggestion ? Thanks!!!

Update: Hmm, I can run googlenet on Android now, but unsure why this works: transform the model from caffe to caffe2 again !!! But need to modify the _deploy.prototxt_ of...

@jerryzh168 Got it. Thanks a lot !!! Since the acceleration by GPU is great, we are looking forward to this implementation.

Hi, I encounter the same problem of multiple boxes on one face. Then, I replace gpu_nms_wrapper with cpu_nms_wrapper, it works for me ~

Hi I encounter the same problem. And I also replace the ransform_tpose.json But I could not generate the normal output. Any suggestions? My environment is: pytorch: 1.6.0 , cuda :10.2...