可以参考原作者：https://github.com/ChenYingpeng/darknet2caffe
一、环境
Python2.7
Caffe
Pytorch >= 0.40
二、caffe参数配置
1. caffe_layers/mish_layer/mish_layer.hpp,caffe_layers/upsample_layer/upsample_layer.hpp into include/caffe/layers/.
2. Copy caffe_layers/mish_layer/mish_layer.cpp mish_layer.cu,caffe_layers/upsample_layer/upsample_layer.cpp upsample_layer.cu into src/caffe/layers/.
3. Copy caffe_layers/pooling_layer/pooling_layer.cpp into src/caffe/layers/.Note:only work for yolov3-tiny,use with caution.
4. Add below code into src/caffe/proto/caffe.proto.
// LayerParameter next available layer-specific ID: 147 (last added: recurrent_param)
message LayerParameter {
optional TileParameter tile_param = 138;
optional VideoDataParameter video_data_param = 207;
optional WindowDataParameter window_data_param = 129;
++optional UpsampleParameter upsample_param = 149; //added by chen for Yolov3, make sure this id 149 not the same as before.
++optional MishParameter mish_param = 150; //added by chen for yolov4,make sure this id 150 not the same as before.
}
// added by chen for YoloV3
++message UpsampleParameter{
++ optional int32 scale = 1 [default = 1];
++}
// Message that stores parameters used by MishLayer
++message MishParameter {
++ enum Engine {
++ DEFAULT = 0;
++ CAFFE = 1;
++ CUDNN = 2;
++ }
++ optional Engine engine = 2 [default = DEFAULT];
++}
然后重新编译caffe
make clean
make all -j8
make pycaffe
三、模型转换
python darknet2caffe.py cfg/yolov3.cfg weights/yolov3.weights prototxt/yolov3.prototxt caffemodel/yolov3.caffemodel
四、模型验证
eval...
