DeepMatching is an algorithm that finds corresponding points in two images.
This wouldn't have been possible without the work of @WIStudent and the gist posted here: https://gist.github.com/WIStudent/08072e8dd41487d2dde7ce75eec3dcbf
cuDNN download requires a free NVIDIA developer account in order to download.
- Visit https://developer.nvidia.com/cudnn
- Click the "DOWNLOAD cuDNN" button
- Login or join
- Review terms
- Click "Archived cuDNN Releases"
- Expand "Download cuDNN v3 (September 8, 2015), for CUDA 7.0 and later."
- Download "cuDNN v3 Library for Linux (Updated August 30th,2016)."
- Create an empty directory
- Copy the Dockerfile and Makefile to the new directory
- Edit Dockerfile line #49 and change the path to cuDNN v3. I use
python -m SimpleHTTPServer 8001
in the directory I downloaded the file and update the URL to my local machine such ashttp://{local_machine_ip_address}:8001/cudnn-7.0-linux-x64-v3.0.8-prod.tgz
- Build
docker build -t deepmatching:gpu .
- Run
docker run -it --rm deepmatching:gpu
cd /root/web_gpudm_1.0/
python deep_matching_gpu.py -GPU 0 liberty1.png liberty2.png
1) from running section,replace docker with nvidia-docker
Build
docker build -t deepmatching:gpu .
->nvidia-docker build -t deepmatching:gpu .
Run
docker run -it --rm deepmatching:gpu
->nvidia-docker run -it --rm deepmatching:gpu
2 )caffe/Makefile.config add CUDA_ARCH for I am using 6.1 cards,
line 35 from
to
and rebuild caffe and deepmatching。
Very thanks for the share。