# Plugin layer is much slower than caffe

**URL:** <https://forums.developer.nvidia.com/t/plugin-layer-is-much-slower-than-caffe/62153>\
**Category:** TensorRT\
**Created:** [June 11, 2018, 7:10am UTC](https://forums.developer.nvidia.com/t/plugin-layer-is-much-slower-than-caffe/62153 "2018-06-11T07:10:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![OnePieceOfDeepLearning](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/onepieceofdeeplearning/32/26116_2.png) [@OnePieceOfDeepLearning](https://forums.developer.nvidia.com/u/OnePieceOfDeepLearning)\
**Post date:** [June 11, 2018, 7:10am UTC](https://forums.developer.nvidia.com/t/plugin-layer-is-much-slower-than-caffe/62153/1 "2018-06-11T07:10:53Z")

</div>

Hi,

I am porting a caffe upsample layer ([add efficient upsample layer by twmht · Pull Request #6384 · BVLC/caffe · GitHub](https://github.com/BVLC/caffe/pull/6384/files)) to a tensorRT plugin.

However, the speed is very slow as compared to caffe.

most of gpu code is identical with caffe.

When upsample input is 256 \* 40 \* 52 (CHW), the processed time is 19.116ms in TensorRT.

However, the processed time with the same input volume in caffe is only 0.03ms.

this is a huge speed gap.

Any idea?