Light

pris-cv / an-erudite-fgvc-model Goto Github PK

View Code? Open in Web Editor NEW

14.0 14.0 4.0 20 KB

Code release for Your “An Erudite Fine-Grained Visual Classification Model (CVPR 2023)"

License: MIT License

Python 100.00%

fine-grained fine-grained-classification fine-grained-recognition fine-grained-visual-categorization multiple-datasets pytorch

an-erudite-fgvc-model's Introduction

An-Erudite-FGVC-Model

Code release for “An Erudite Fine-Grained Visual Classification Model" (CVPR 2023)

Changelog

2023/04/18 upload the code.

Requirements

python 3.6
PyTorch 1.7.1+cu110
torchvision 0.8.2+cu110
learn2learn 0.1.7

Data

Download datasets
Extract them to data/cars/, data/birds/ and data/airs/, respectively.
Split the dataset into train and test folder, the index of each class should follow the Birds.xls, Air.xls, and Cars.xls

e.g., CUB-200-2011 dataset

  -/birds/train
	         └─── 001.Black_footed_Albatross
	                   └─── Black_Footed_Albatross_0001_796111.jpg
	                   └─── ...
	         └─── 002.Laysan_Albatross
	         └─── 003.Sooty_Albatross
	         └─── ...
   -/birds/test	
             └─── ...

Training

CUDA_VISIBLE_DEVICES=X python main.py (Mix Cars and Flowers)

Citation

If you find this paper useful in your research, please consider citing:

@InProceedings{Chang2023Erudite,
  title={An Erudite Fine-Grained Visual Classification Model},
  author={Chang, Dongliang and Tong, Yujun and Du, Ruoyi and Timothy, Hospedales and Song, Yi-Zhe and Ma, Zhanyu },
  booktitle = {Computer Vision and Pattern Recognition},
  year={2023}
}

Contact

Thanks for your attention! If you have any suggestion or question, you can leave a message here or contact us directly:

an-erudite-fgvc-model's People

Contributors

Stargazers

Watchers

Forkers

dongliangchang myoh97 fmujie

an-erudite-fgvc-model's Issues

About the parallel bug in the code

Thanks for your kindly sharing code. There is an issue, when running the code with two or more cards (using dataparallel), the error happens as follows. Could you please share your solution? It would be very helpful. Single card is ok, but it is two slow for training.

Besides, could you please share your paper in a arxiv version? Then more details can be found and your excellent work can be spread more fluently. Thank you very much.

Traceback (most recent call last):
File "main.py", line 440, in
train(epoch)
File "main.py", line 341, in train
task_model.adapt(adaptation_loss) # computes gradient, update task_model in-place
File "/home/sunhongbo/anaconda3/envs/u_modal/lib/python3.6/site-packages/learn2learn/algorithms/maml.py", line 169, in adapt
self.module = maml_update(self.module, self.lr, gradients)
UnboundLocalError: local variable 'gradients' referenced before assignment

Detailed performance per datasets under training separately and joint training on 4 datasets.

Thanks for your great work! I noticed only mean acc is provided in Table 2. Is it possible share the detailed performance per datasets under training separately and joint training on 4 datasets?

Or is this detailed performance per datasets on training separately ?

Looking forward to your reply, thanks!

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.