Edit model card

VICReg ResNet-50

ResNet-50 pretrained with VICReg. VICReg was introduced in VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning, while ResNet was introduced in Deep Residual Learning for Image Recognition. The official implementation of a VICReg Resnet-50 can be found here.

Weights converted from the official VICReg ResNet using this script.

For up-to-date model card information, please see the original repo.

How to use

Warning: The feature extractor in this repo is a copy of the one from microsoft/resnet-50. We never verified if this image prerprocessing is the one used with VICReg ResNet-50.

from transformers import AutoFeatureExtractor, ResNetModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = AutoFeatureExtractor.from_pretrained('Ramos-Ramos/vicreg-resnet-50')
model = ResNetModel.from_pretrained('Ramos-Ramos/vicreg-resnet-50')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state

BibTeX entry and citation info

  title={Vicreg: Variance-invariance-covariance regularization for self-supervised learning},
  author={Bardes, Adrien and Ponce, Jean and LeCun, Yann},
  journal={arXiv preprint arXiv:2105.04906},
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.

Dataset used to train Ramos-Ramos/vicreg-resnet-50