search

ethanhe42 / channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
https://arxiv.org/abs/1707.06168
MIT License
1.08k stars 310 forks source link

inference time's Comparison : original vgg16 vs cVGG-16_3C4x #106

Closed peternara closed 6 years ago

peternara commented 6 years ago

Hi. I try to finetuning about each imagenet pre-trained model(original vgg16 vs VGG-16_3C4x) using my new data. I was successful learning(finetuning) using the channel_pruning_VGG-16_3C4x model you provided. When referring to only a single image, the inference time is not different from the original model.

"https://github.com/yihui-he/channel-pruning/wiki/inference-time-on-GPU" is very different from here. Could you tell me why? @yihui-he

ethanhe42 commented 6 years ago

I don’t know.