Lucasc-99/PackNet-Continual-Learning
The PackNet Continual Learning Method in Pytorch
This project helps machine learning practitioners who need to train a single neural network on a sequence of different tasks without forgetting previously learned knowledge. It takes a pre-trained neural network and a new task's dataset as input, then outputs an updated network that can perform well on both the old and new tasks. This is ideal for researchers and engineers working on intelligent systems that adapt over time.
No commits in the last 6 months.
Use this if you need to continually update a machine learning model with new information or tasks, rather than retraining a new model from scratch each time.
Not ideal if you are looking for a simple, off-the-shelf solution for single-task training or if your tasks are completely unrelated and don't benefit from shared network capacity.
Stars
15
Forks
2
Language
Python
License
—
Category
Last pushed
Aug 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Lucasc-99/PackNet-Continual-Learning"
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.