GitXplorerGitXplorer
l

CLIP

public
77 stars
10 forks
1 issues

Commits

List of commits on branch main.
Verified
36d07826ec6ac8e63686a828646636199ca0b18c

Update README.md

lleaderj1001 committed 4 years ago
Unverified
7eb1f34557c293fe6b55b2dd885a684f9306c417

update train code

lleaderj1001 committed 4 years ago
Unverified
9622285dffe968d33d4c3fb0c4f9cd4ae054258c

init

lleaderj1001 committed 4 years ago
Unverified
6066dd3d6a803cafe6fbfd42dd3bb9d70d313fbf

init

lleaderj1001 committed 4 years ago
Unverified
9cfc7d394baf6085fd6532b7d38fe0dc89bbc411

init

lleaderj1001 committed 4 years ago
Verified
2a846f46c8182b463710b95929d310afb9435c7b

Update README.md

lleaderj1001 committed 4 years ago

README

The README file for this repository.

CLIP (Contrastive Language–Image Pre-training)

Experiments (Evaluation)

Model Dataset Acc (%)
ViT-B/32 (Paper) CIFAR100 65.1
ViT-B/32 (Our) CIFAR100 61.71
ViT-B/32 (Paper CIFAR10 91.3
ViT-B/32 (Our) CIFAR10 88.8

Overview

model

Training

  • Work In Process

Usage

  • Evaluation
python evaluation.py --dataset CIFAR100 --cuda True
  • args
    • dataset (str): CIFAR10, CIFAR100 (default: CIFAR100)
    • num_workers (int): default: 0
    • batch_size (int): default: 128
    • cuda (bool): False
  • Training
    • Prepare Data
      • Visual Genome Dataset link
      • Download (images, region descriptions)
    • training
    python main.py --base_dir ./ --cuda True

Reference

  • paper link
  • Author: Alec Radford, Jong Wook Kim, Chris Hallacy, Girish Sastry, Amanda Askell, Pamela Mishkin, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Jack Clark, Gretchen Krueger, Ilya Sutskever
  • OpenAI