Light

yannadani / dlgm Goto Github PK

View Code? Open in Web Editor NEW

53.0 8.0 15.0 56.29 MB

Implementation of the paper 'Deep Learning of Graph Matching', CVPR 2018.

License: MIT License

Python 100.00%

dlgm's Introduction

Deep Learning of Graph Matching

This is an implementation of the paper "Deep Learning of Graph Matching", CVPR, 2018. Note: This is not an official implementation.

To run the above code, install the dependecies as listed in environment.yml. The easiest way to do this is to setup a conda environemnt

conda env create -f environment.yml

conda activate dlgm

Then update the parameters in the config_sintel.py script according to your hardware availability and needs.

Training the network

python main.py --dataset sintel --data_path path/to/sintel/root

Note that only sintel dataset is supported as of now. We are not able to exactly reproduce the results of the paper. But the graph matching layers corresponding to optical flow has been tested for correctness. A primitive implementation of the Bistochastic layer is available but is not tested.

Contributing

There is lot of scope for improvements with respect to the performance. PR's and discussion in this regard or any general matter on this topic is welcome :)

dlgm's People

Contributors

Stargazers

Watchers

Forkers

hnczwj2008 swg209 gsunfeng leizhiqin xjliu1204 hmchuong shi27feng gaopeng5 japezhang 2413917906 jinshiyin freegliboracle a2006020805 gangma2610 wangyinyan1998

dlgm's Issues

how to compute the bi-stochastic matrix

Hello, In the main.py/class VGG_graph_matching/biStochastic_forward() function:

S = v.view(n,m)
for i in range(N):
        S = torch.mm(S, torch.mm(torch.ones(1,n),S).inverse())
        S = torch.mm(torch.mv(S, torch.ones(m,1)).inverse(), S)
return S

The A.inverse() function need the matrix A to be a square matrix, so this cannot work?

how to v

Error while running main.py

Hello,

I tried running the command python main.py --dataset sintel --data_path ~/Desktop/jug-pc-x/05_Repositories/dlgm/ and run into the following error. Any suggestions on what could be the issue? (I have cudatoolkit 9.0 and pytorch 1.1.0 setup in the environment). Thank you for your time!

log path logs/sintel/sintel_seed-7.log
Using 1 GPUs!
Traceback (most recent call last):
  File "main.py", line 294, in <module>
    model = model.to(args.device)
  File "/home/manan/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 386, in to
    return self._apply(convert)
  File "/home/manan/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 193, in _apply
    module._apply(fn)
  File "/home/manan/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 199, in _apply
    param.data = fn(param.data)
  File "/home/manan/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 384, in convert
    return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
RuntimeError: CUDA error: unknown error

about the experiments results

Hi, thanks for your reproducing. And I want to know have you test the code on the datasets in the paper? I mean I will be very appreciated if you could provide more information about this paper.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.