isaaccorley/simsiam-pytorch
PyTorch Implementation of SimSiam from "Exploring Simple Siamese Representation Learning" by Chen et al.
This helps deep learning engineers pre-train image classification models more effectively, especially when they have limited labeled data. It takes in raw, unlabeled image datasets and outputs a powerful, pre-trained encoder model. This encoder can then be fine-tuned with a small amount of labeled data to achieve high-performance image classification. Deep learning researchers and practitioners who build computer vision systems would find this tool beneficial.
No commits in the last 6 months.
Use this if you are a deep learning engineer working on image classification and need to improve model performance by leveraging large amounts of unlabeled image data for pre-training, before fine-tuning with a smaller labeled dataset.
Not ideal if you are not a deep learning engineer or do not have experience with PyTorch and deep learning model training.
Stars
17
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 11, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/isaaccorley/simsiam-pytorch"
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