search

ethanhe42 / channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
https://arxiv.org/abs/1707.06168
MIT License
1.07k stars 310 forks source link

GPU memory consume #41

Closed gaqiness closed 6 years ago

gaqiness commented 6 years ago

All are welcome to create issues, but please google the problem first, and make sure it has not already been reported.

What steps reproduce the bug?

Hi I test the VGG-16 as follow command caffe test -model channel_pruning_VGG-16_3C4x.prototxt -weights channel_pruning_VGG-16_3C4x.caffemodel -iterations 5000 -gpu 0 compare the performance of original vgg-16, I found that the memory of GPU is increased.

The test result of GPU memory consume in nvidia GTX1080: channel_pruning_VGG-16_3C4x.caffemodel : 1773MB original_VGG-16.caffemodel: 1503MB ps: batch_size=10

why does it increase so much? Is that normal?

What hardware and operating system/distribution are you running?

Operating system: ubuntu16.04 CUDA version: 8.0 CUDNN version: 6.0 openCV version: 2.4.9 BLAS:
Python version: 3.5

If the bug is a crash, provide the backtrace.

ethanhe42 commented 6 years ago

Please see this post: https://github.com/yihui-he/channel-pruning/wiki/inference-time-on-GPU

gaqiness commented 6 years ago

I don't understand . why GPU memory would increased in channel-pruning model. thanks!

ethanhe42 commented 6 years ago

Please read 3C part in paper

gaqiness commented 6 years ago

many thanks