https://github.com/flyingpot/pytorch_deephash

Pytorch implementation of Deep Learning of Binary Hash Codes for Fast Image Retrieval, CVPRW 2015
https://github.com/flyingpot/pytorch_deephash

deep-learning deephash hash image-retrieval pytorch

Last synced: about 3 hours ago
JSON representation

Pytorch implementation of Deep Learning of Binary Hash Codes for Fast Image Retrieval, CVPRW 2015

• Host: GitHub
• URL: https://github.com/flyingpot/pytorch_deephash
• Owner: flyingpot
• License: mit
• Created: 2017-10-11T11:41:43.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2021-07-19T11:34:55.000Z (over 3 years ago)
• Last Synced: 2024-11-08T17:16:06.529Z (8 days ago)
• Topics: deep-learning, deephash, hash, image-retrieval, pytorch
• Language: Python
• Homepage:
• Size: 27.3 KB
• Stars: 187
• Watchers: 8
• Forks: 48
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# pytorch_deephash

## Introduction

This is the Pytorch implementation of [Deep Learning of Binary Hash Codes for Fast Image Retrieval](https://github.com/kevinlin311tw/caffe-cvprw15), and can achieve more than 93% mAP in CIFAR10 dataset.

## Environment

> Pytorch 1.4.0

>

> torchvision 0.5.0

>

> tqdm

>

> numpy

## Training

```bash

python train.py

```

You will get trained models in model folder by default, and models' names are their test accuracy.

## Evaluation

```bash

python evaluate.py --pretrained {your saved model name in model folder by default}

```

## Tips

1. If using Windows, keep num_works zero

2. There are some other args, which you can get them by adding '-h' or reading the code.