Darknet YOLOv3 on Jetson Nano

推荐比较好的博客：https://ai4sig.org/2019/06/jetson-nano-darknet-yolov3/

用的AlexeyAB的版本，并且给出了yolov3和tiny的效果对比。

出现nvcc not found 的错误，参考如下解决

http://www.neko.ne.jp/~freewing/raspberry_pi/nvidia_jetson_nano_nvcc_not_found/

● Jetson Nano nvcc: not found build CUDA app Error

　NVIDIA Jetson Nanoで nvcc not found build CUDA app Errorの対応方法
　Jetson Nanoで CUDAを使用したアプリをビルドする時に nvcc not foundが出る場合の対処方法

　解決方法：nvccにパスを通す

# nvcc not found
$ make
....
....
/bin/sh: 1: nvcc: not found
Makefile:92: recipe for target 'obj/convolutional_kernels.o' failed
make: *** [obj/convolutional_kernels.o] Error 127

$ /usr/local/cuda/bin/nvcc
nvcc fatal   : No input files specified; use option --help for more information

$ /usr/local/cuda/bin/nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sun_Sep_30_21:09:22_CDT_2018
Cuda compilation tools, release 10.0, V10.0.166

# 解決方法：nvccにパスを通す
$ export PATH=${PATH}:/usr/local/cuda/bin

还会遇到安装skimage（scikit-image）失败的错误：可以参考https://blog.csdn.net/beckhans/article/details/89146881

比如升级pip到19，或者安装一些依赖，具体不知道哪个步骤是关键。