Makefile:92: recipe for target 'obj/convolutional_kernels.o' failed

单独用GPU编译darknet源码时出现如下错误：

解决方法： 修改Makefile

NVCC = /usr/local/cuda-9.0/bin/nvcc

重新编译，错误解决

make

测试一下GPU版本的yolov3

./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

出现如下错误：

./darknet: error while loading shared libraries: libcudart.so.9.0: cannot open shared object file: No such file or directory

解决方法：

sudo cp /usr/local/cuda-9.0/lib64/libcudart.so.9.0 /usr/local/lib/libcudart.so.9.0 && sudo ldconfig 
sudo cp /usr/local/cuda-9.0/lib64/libcublas.so.9.0 /usr/local/lib/libcublas.so.9.0 && sudo ldconfig 
sudo cp /usr/local/cuda-9.0/lib64/libcurand.so.9.0 /usr/local/lib/libcurand.so.9.0 && sudo ldconfig

若出现

./darknet: error while loading shared libraries: libcudnn.so.7: cannot open shared object file: No such file or directory

则

sudo cp /usr/local/cuda/lib64/libcudnn.so.7 /usr/local/lib/libcudnn.so.7
sudo ldconfig

若出现

CUDA Error: unknown error
darknet: ./src/cuda.c:36: check_error: Assertion `0' failed.
Aborted (core dumped)

加上sudo

若出现：

    5 CUDA Error: out of memory
darknet: ./src/cuda.c:36: check_error: Assertion `0' failed.
Aborted (core dumped)

参考：https://blog.csdn.net/wukai0909/article/details/97539472