Caffe-ShuffleNet

Caffe-ShuffleNet copied to clipboard

Training schedule

3

Hi @camel007 , ShuffleNet is a great idea and the model size is apparently reduced. Have you ever tried to train it on imagenet? I only got 64% as top1...

leochli

Why is temp_blob_ necessary?

3

I noticed that the current shuffle operation use `temp_blob_` as the intermediate variable for memory copy. Why can't we just set top_data as the "output" argument of `Resize_gpu`?

nicklhy

Letsgetit38