常用命令记录
./darknet detector test <data_cfg> <models_cfg> <weights> <test_file> [-thresh] [-out]
./darknet detector train <data_cfg> <models_cfg> <weights> [-thresh] [-gpu] [-gpus] [-clear]
./darknet detector valid <data_cfg> <models_cfg> <weights> [-out] [-thresh]
./darknet detector recall <data_cfg> <models_cfg> <weights> [-thresh]
'<>'必选项,’[ ]‘可选项
data_cfg:数据配置文件,eg:cfg/voc.data
models_cfg:模型配置文件,eg:cfg/yolov3-voc.cfg
weights:权重配置文件,eg:weights/yolov3.weights
test_file:测试文件,eg://*/test.txt
-thresh:显示被检测物体中confidence大于等于 [-thresh] 的bounding-box,默认0.005
-out:输出文件名称,默认路径为results文件夹下,eg:-out “” //输出class_num个文件,文件名为class_name.txt;若不选择此选项,则默认输出文件名为comp4_det_test_“class_name”.txt
-i/-gpu:指定单个gpu,默认为0,eg:-gpu 2
-gpus:指定多个gpu,默认为0,eg:-gpus 0,1,2
正常情况下,很多时候都是直接使用预训练模型进行训练
./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74
操作问题
运行时ctrl+c停止运行,有时候操作会误停
如果出现意外还可以继续使用之前运行保存的.backup文件进行训练
./darknet detector train cfg/coco.data cfg/yolov3.cfg backup/yolov3.backup
如果加上-clear 则模型会从初始状态开始
./darknet detector train cfg/coco.data cfg/yolov3.cfg backup/yolov3.backup -clear
运行问题
./darknet: error while loading shared libraries: libcudnn.so.8: cannot open
cudnn.h:60:10: fatal error: cudnn_version.h: 没有那个文件或目录%20%20 60 | #
之前的cmd运行是
sudo cp cuda/include/cudnn.h /usr/local/cuda/include
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn.h /usr/local/cuda/lib64/libcudnn*
现在应该重新运行
sudo cp cuda/include/cudnn*.h /usr/local/cuda/include
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn.h /usr/local/cuda/lib64/libcudnn*
参照链接:
https://github.com/pjreddie/darknet/issues/2356
https://blog.csdn.net/xgd2016/article/details/107480633