sayakpaul/SimCLR-in-TensorFlow-2
(Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.
This project helps machine learning engineers build robust image classification models, especially when labeled data is scarce. It takes unlabeled image datasets and applies a technique called SimCLR to learn meaningful visual features without human supervision. The output is a pre-trained model capable of excellent performance on downstream image recognition tasks with minimal labeled examples.
No commits in the last 6 months.
Use this if you need to train high-performing image recognition models but have limited access to extensive labeled datasets for supervised training.
Not ideal if you already have a large, well-labeled dataset for your specific image classification task, as traditional supervised learning might be simpler.
Stars
89
Forks
21
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 06, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sayakpaul/SimCLR-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