Chainer - 3. 실습

https://github.com/DeNA/Chainer_Realtime_Multi-Person_Pose_Estimation

Convert 부분까지만 여기에 작성하고 나머지는 위 사이트를 따라하면 되요.

Convert Caffe model to Chainer model

The authors of the original implementation provide trained caffe model which you can use to extract model weights. Execute the following commands to download the trained model and convert it to npz file:

#models 디렉토리로 이동해서 wget으로 cafemodel 을 다운받아요. 그리고 model을 이용해서 npz 파일을 생성해요. 

cd models
wget http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/coco/pose_iter_440000.caffemodel
wget http://posefs1.perception.cs.cmu.edu/OpenPose/models/face/pose_iter_116000.caffemodel
wget http://posefs1.perception.cs.cmu.edu/OpenPose/models/hand/pose_iter_102000.caffemodel
python convert_model.py posenet pose_iter_440000.caffemodel coco_posenet.npz
python convert_model.py facenet pose_iter_116000.caffemodel facenet.npz
python convert_model.py handnet pose_iter_102000.caffemodel handnet.npz
cd ..

아래처럼 나오면 성공. 실제 models 디렉토리에 coco_posenet.npz 파일이 생성됐는지 확인해요