8000 GitHub - ark10806/Meow: final-project-level3-cv-03 created by GitHub Classroom
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

ark10806/Meow

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🐱 Korean Zero-shot Cat Emotion and Action Understanding.

Official Pytorch Implementation

Teaser image

💾 Installation

For all the methods described in the paper, is it required to have:

Specific requirements for each method are described in its section. To install CLIP please run the following commands:

conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=<CUDA_VERSION>
pip install ftfy regex tqdm gdown
pip install git+https://github.com/openai/CLIP.git

🔨 Method

Method image

1. CLIP-based Contrastive Latent Representation Learning.

Dataset Curation.

We create an MSCOCO and WiT Kor 5BE2 ean-Image-English Pair dataset.

Training.

python3 train.py

⛳ Results

Zero-shot Image Classification Accuracy.

  • Cifar10
Model Acc.
KoCLIP(kor) 15%
Ours(kor) 80%
CLIP(eng) 95%

Proxy Server

ezgif-2-01fa745b2d http://pred.ga/AI_Tech/FinalProject/GPU2.mp4 (High-quality video)

Cat Diary Generation Results.

Demo.

LSUN image

About

final-project-level3-cv-03 created by GitHub Classroom

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0