Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

Learning-Similarity-Conditions

alt text

This repository contains a PyTorch implementation of the paper Learning Similarity Conditions Without Explicit Supervision accepted at ICCV 2019. It is based on the official implementation of the Conditional Similarity Networks paper. If you find this implementation or the paper helpful, please consider citing:

@InProceedings{tanSimilarity2019,
author={Reuben Tan and Mariya I. Vasileva and Kate Saenko and Bryan A. Plummer},
title={Learning Similarity Conditions Without Explicit Supervision},
booktitle={ICCV},
year={2019} }

Dependencies

  1. Python 2.7
  2. Pytorch version 0.1.12

Download Data

To download the Zappos dataset as well as the training, validation and test triplets: python get_data.py

Usage

To train the network with the hyperparameter setttings used in the paper,

python main.py --name {your experiment name} --learned --num_traintriplets 200000

When training is done, run the following script to evaluate the trained model on the test set:

python main.py --test --resume runs/{your experiment name}/model_best.pth.tar

We trained our model on a single GTX 1080 GPU on a CentOS system.

Contact

Please do not hesitate to contact me at rxtan@bu.edu if you have any questions or problems running the code.

About

No description, website, or topics provided.

Resources

Releases

No releases published

Packages

No packages published

Languages