Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
GitHub / ArthurZucker / RecvisProject
In this project, we propose to study Vision Transformers trained using the Barlow Twins self-supervised method, and compare the results with DINO. We demonstrate the effectiveness of the Barlow Twins method by showing that networks pretrained on the small PASCAL VOC 2012 dataset are able to generalize well. Authors: Apavou Clément & Zucker Arthur
JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArthurZucker%2FRecvisProject
Stars: 13
Forks: 2
Open Issues: 2
License: gpl-3.0
Language: Python
Repo Size: 10.9 MB
Dependencies:
19
Created: over 2 years ago
Updated: 4 months ago
Last pushed: 8 months ago
Last synced: about 1 month ago
Topics: computer-vision, pytorch, self-supervised-learning, semantic-segmentation
Files
Dependencies
- Pillow ==9.0.0
- albumentations ==1.1.0
- easydict ==1.9
- einops ==0.4.0
- helpers ==0.2.0
- layers ==0.1.5
- matplotlib ==3.3.2
- numpy ==1.22.0
- pandas ==1.1.3
- pytorch_lightning ==1.5.7
- pytorch_pretrained_vit ==0.0.7
- scikit_learn ==1.0.1
- seaborn ==0.11.0
- simple_parsing ==0.0.18
- skimage ==0.0
- timm ==0.5.4
- torch ==1.10.1
- torchvision ==0.11.2
- vit_pytorch ==0.26.4