Jetson TX1安装 Pytorch

大体流程

1. 重装系统

先重装了系统，避免混乱的旧系统所带来的不必要麻烦。

安装依赖包

sudo apt-get install python3-pip cmake
pip3 install numpy pyyaml mkl mkl-include setuptools cffi typing
# 各大教程里面还推荐了安装其他的一些包，我也不知道有没有用。

下载Pytorch源码

# 如果你想安装历史版本，可下载对应版本的源码，或者git checkout
git clone --recursive http://github.com/pytorch/pytorch
cd pytorch

安装源码中要求的Python依赖包

sudo pip3 install -r requirements.txt

安装

# 直接安装
sudo python3 setup.py install

# 生成whl
python3 setup.py bdist_wheel

附安装的参考链接：

1. https://gist.github.com/dusty-nv/ef2b372301c00c0a9d3203e42fd83426
2. https://github.com/andrewadare/jetson-tx2-pytorch
3. PyTorch for Jetson Nano - NVIDIA Developer Forums
4. https://github.com/dusty-nv/jetson-reinforcement/blob/master/CMakePreBuild.sh

可能遇到的问题：

1. 内存不足

# 显示的错误信息没保存下来
# 好像是什么内部错误 

解决办法：添加交换分区
附添加分区的参考链接：
https://help.ubuntu.com/community/SwapFaq#How_do_I_add_or_modify_a_swap_partition.3F
https://www.jetsonhacks.com/2016/12/21/jetson-tx1-swap-file-and-development-preparation/

2. NCCL编译报错

Makefile:68: recipe for target '/home/ubuntu/software/pytorch/build/nccl/obj/collectives/device/devlink.o' failed
make[5]: *** [/home/ubuntu/software/pytorch/build/nccl/obj/collectives/device/devlink.o] Error 255
Makefile:44: recipe for target '/home/ubuntu/software/pytorch/build/nccl/obj/collectives/device/colldevice.a' failed
make[4]: *** [/home/ubuntu/software/pytorch/build/nccl/obj/collectives/device/colldevice.a] Error 2
Makefile:25: recipe for target 'src.build' failed
make[3]: *** [src.build] Error 2
CMakeFiles/nccl_external.dir/build.make:110: recipe for target 'nccl_external-prefix/src/nccl_external-stamp/nccl_external-build' failed
make[2]: *** [nccl_external-prefix/src/nccl_external-stamp/nccl_external-build] Error 2
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/nccl_external.dir/all' failed
make[1]: *** [CMakeFiles/nccl_external.dir/all] Error 2

由于TX1默认情况并没有安装NCCL，因此为了避免报错，可对CMakeLists.txt和setup.py进行如下更改：

# append to setup.py
USE_NCCL = False
# USE_DISTRIBUTED = False

# change the option in the CMakeLists.txt
option(USE_NCCL "Use NCCL" OFF)

修改参数之后，建议clean一下！！！