Git Product home page Git Product logo

semicon's Introduction

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval


Environment

Python 3.8.5
Pytorch 1.10.0
torchvision 0.11.1
numpy 1.19.2 loguru 0.5.3 tqdm 4.54.1


Dataset

We use the following 5 datasets: CUB200-2011, Aircraft, VegFru, Food101 and NABirds.


Train

We train our model in only one 2080Ti card, for different datasets, we provide different sample training commands:

The CUB200-2011 dataset:

 python run.py --dataset cub-2011 --root /dataset/CUB2011/CUB_200_2011 --max-epoch 30 --gpu 0 --arch semicon --batch-size 16 --max-iter 40 --code-length 12,24,32,48 --lr 2.5e-4 --wd 1e-4 --optim SGD --lr-step 40 --num-samples 2000 --info 'CUB-SEMICON' --momen=0.91

The Aircraft dataset:

 python run.py --dataset aircraft --root /dataset/aircraft/ --max-epoch 30 --gpu 0 --arch semicon --batch-size 16 --max-iter 40 --code-length 12,24,32,48 --lr 2.5e-4 --wd 1e-4 --optim SGD --lr-step 40 --num-samples 2000 --info 'Aircraft-SEMICON' --momen=0.91

The VegFru dataset:

 python run.py --dataset vegfru --root /dataset/vegfru/ --max-epoch 30 --gpu 0 --arch semicon --batch-size 16 --max-iter 50 --code-length 12,24,32,48 --lr 5e-4 --wd 1e-4 --optim SGD --lr-step 45 --num-samples 4000 --info 'VegFru-SEMICON' --momen=0.91

The Food101 dataset:

 python run.py --dataset food101 --root /dataset/food101/ --max-epoch 30 --gpu 0 --arch semicon --batch-size 16 --max-iter 50 --code-length 12,24,32,48 --lr 2.5e-4 --wd 1e-4 --optim SGD --lr-step 45 --num-samples 2000 --info 'Food101-SEMICON' --momen 0.91

The NAbirds dataset:

 python run.py --dataset nabirds --root /dataset/nabirds/ --max-epoch 30 --gpu 0 --arch semicon --batch-size 16 --max-iter 50 --code-length 12,24,32,48 --lr 5e-4 --wd 1e-4 --optim SGD --lr-step 45 --num-samples 4000 --info 'NAbirds-SEMICON' --momen=0.91

Test

Taking the CUB200-2011 dataset as an example, the testing command is:

 python run.py --dataset cub-2011 --root /dataset/CUB2011/CUB_200_2011 --gpu 0 --arch test --batch-size 16 --code-length 12,24,32,48 --wd 1e-4 --info 'CUB-SEMICON'

semicon's People

Contributors

aassxun avatar hl271 avatar pphuc25 avatar

Stargazers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

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

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

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

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.