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 Transformer，DEiT，Swin Transformer，CvT，T2T-ViT，MLP-Mixer，XCiT，ConvNeXt，PVTv2 等基础视觉算法
PASSL helps machine learning engineers and researchers accelerate their work in computer vision. It provides pre-built, state-of-the-art models for self-supervised learning, allowing you to train powerful image recognition systems with less labeled data. You provide images, and it outputs trained models that understand visual features, ready for specialized tasks like classifying objects or detecting anomalies.
287 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to train high-performing computer vision models but have limited access to extensively labeled image datasets, or want to explore the latest self-supervised learning techniques.
Not ideal if you are looking for a simple, out-of-the-box solution for a very specific, pre-defined image classification problem without custom training.
Stars
287
Forks
67
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 01, 2023
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PaddlePaddle/PASSL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification
microsoft/Semi-supervised-learning
A Unified Semi-Supervised Learning Codebase (NeurIPS'22)