JH-LEE-KR/l2p-pytorch
PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22
This is a developer tool that helps machine learning engineers train models that can continuously learn new information without forgetting previously learned data. It takes image datasets like CIFAR-100 or a combination of datasets, and outputs a trained model with improved accuracy and reduced forgetting over time. Machine learning engineers and researchers working on computer vision tasks with evolving data would find this useful.
201 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer building computer vision models and need to train them incrementally on new data while retaining performance on older data.
Not ideal if you are looking for a plug-and-play solution for general image classification without the need for continual learning capabilities.
Stars
201
Forks
26
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JH-LEE-KR/l2p-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.