sayakpaul/Supervised-Contrastive-Learning-in-TensorFlow-2
Implements the ideas presented in https://arxiv.org/pdf/2004.11362v1.pdf by Khosla et al.
This project provides practical examples for improving image classification models. By taking your labeled image datasets, it shows how to apply an advanced training technique called Supervised Contrastive Learning. The outcome is a more robust and accurate image classification model, making it useful for machine learning engineers and researchers who develop and deploy image recognition systems.
133 stars. No commits in the last 6 months.
Use this if you are a machine learning practitioner looking to enhance the accuracy of your image classification models using state-of-the-art training methods.
Not ideal if you are looking for a plug-and-play solution without understanding or modifying deep learning code.
Stars
133
Forks
23
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 21, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sayakpaul/Supervised-Contrastive-Learning-in-TensorFlow-2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification