NeighConsensus

NCNet Re-implementation on Pytorch 1.0 + Python3.6 (Original implementation : https://github.com/ignacio-rocco/ncnet) For more information check out their project website and their paper on arXiv.

Table of Content

To download Pre-trained feature extractor (ResNet 18 ):

cd model/FeatureExtractor
bash download.sh

To download PF Pascal Dataset :

cd data/pf-pascal/
bash download.sh

For important functions, we provide a quick search here

To train on PF-Pascal :

bash demo_train.sh

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
data/pf-pascal		data/pf-pascal
model		model
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
dataloader.py		dataloader.py
demoMatch.ipynb		demoMatch.ipynb
demo_train.sh		demo_train.sh
eval.py		eval.py
evalPascalPckDataloader.py		evalPascalPckDataloader.py
eval_plot.py		eval_plot.py
loss.py		loss.py
train.py		train.py
trainValidPCK.py		trainValidPCK.py