法米
法米
@yanyanxixi Have you make pycaffe successfully?
@jianan86 I haven't trained alexnet or caffenet, so I can't compare their speed with shufflenet, but i can give you the shufflenet's training speed on my card: GTX1080, shufflenet_1x_g3_deploy.prototxt, batchsize=64,...
@linchaozhang The model is still training right now.
@leolee96 Do you mean the stride=2 case? Yeah, its my mistake, i have fixed it. Thanks.
@linchaozhang @KeyKy @leolee96 @ananddb90 The pre-trained model is released, please check ReadMe file.
@linchaozhang I think you may had a mistake，cause the model is trained with the deploy prototxt file. BTW，how can you get the model's layer output？
@linchaozhang Sorry for that I updated the deploy file 9 days ago, you may not follow it. Please check the update info. https://github.com/farmingyard/ShuffleNet/commit/fdb6e836072581cd465de2d9d07bc6571be86fca
@xchani Just crop and mirror.
@fujihuang @yunren Sorry for some reasons that I can't release the pre-trained model any more.
@wm901115nwpu You can reference to the deploy file and other issues.