# DeepMatching GPU version on Ubuntu 16.04 (Docker)
[DeepMatching](http://lear.inrialpes.fr/src/deepmatching/) is an algorithm that finds corresponding points in two images.

## Thanks @WIStudent
This wouldn't have been possible without the work of @WIStudent and the gist posted
here: https://gist.github.com/WIStudent/08072e8dd41487d2dde7ce75eec3dcbf

# cuDNN v3
cuDNN download requires a free NVIDIA developer account in order to download.
1. Visit https://developer.nvidia.com/cudnn
1. Click the "DOWNLOAD cuDNN" button
1. Login or join
1. Review terms
1. Click "Archived cuDNN Releases"
1. Expand "Download cuDNN v3 (September 8, 2015), for CUDA 7.0 and later."
1. Download "cuDNN v3 Library for Linux (Updated August 30th,2016)."

## Running
1. Create an empty directory
1. Copy the Dockerfile and Makefile to the new directory
1. 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 as `http://{local_machine_ip_address}:8001/cudnn-7.0-linux-x64-v3.0.8-prod.tgz`
1. Build `docker build -t deepmatching:gpu .`
1. Run `docker run -it --rm deepmatching:gpu`
1. `cd /root/web_gpudm_1.0/`
1. `python deep_matching_gpu.py -GPU 0 liberty1.png liberty2.png`