加入CODE CHINA

· 不限速    · 不限空间    · 不限人数    · 私仓免费

免费加入
README.md

Deformable Convolutional Networks V2 with Pytorch 1.X

Build

    ./make.sh         # build
    python testcpu.py    # run examples and gradient check on cpu
    python testcuda.py   # run examples and gradient check on gpu 

Note

Now the master branch is for pytorch 1.x, you can switch back to pytorch 0.4 with,

git checkout pytorch_0.4

Known Issues:

  • Gradient check w.r.t offset (solved)
  • Backward is not reentrant (minor)

This is an adaption of the official Deformable-ConvNets.

Update: all gradient check passes with double precision.

Another issue is that it raises RuntimeError: Backward is not reentrant. However, the error is very small (<1e-7 for float <1e-15 for double), so it may not be a serious problem (?)

Please post an issue or PR if you have any comments.

项目简介

🚀 Github 镜像仓库 🚀

源项目地址

https://github.com/charlesshang/dcnv2

发行版本

当前项目没有发行版本

贡献者 3

C charles @charles
D Daniel Kurnia Suhendro @Daniel Kurnia Suhendro
F Fredrik Trobro @Fredrik Trobro

开发语言

  • C++ 39.8 %
  • Cuda 33.4 %
  • Python 20.1 %
  • C 6.7 %
  • Shell 0.0 %