thuml/Xlearn
Transfer Learning Library
This library helps machine learning researchers and practitioners adapt models trained on one type of data to perform well on a different, but related, dataset without needing to retrain from scratch. It takes an existing trained model and a new dataset, providing methods to adjust the model for the new domain. This is primarily for those working on advanced machine learning research and application development.
463 stars. No commits in the last 6 months.
Use this if you need to apply a machine learning model from one domain (e.g., images of cats) to a different, but related, domain (e.g., images of dogs) where you have limited labeled data for the new domain.
Not ideal if you are looking for a general-purpose machine learning library for standard tasks like classification or regression, or if you prefer using TensorFlow, as this version is older and a newer library is recommended.
Stars
463
Forks
154
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Xlearn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...