Tensorflow and Theano + Lasagne codes for the paper https://arxiv.org/abs/1611.07725
The main features of srebuffi/icarl are: Continual Learning Frameworks.
Open-source alternatives to srebuffi/icarl include: aimagelab/lider — Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning". aimagelab/mammoth — An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for… ariseff/overcoming-catastrophic — Implementation of "Overcoming catastrophic forgetting in neural networks" in Tensorflow. arunmallya/packnet — Code for PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning. arunmallya/piggyback — Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights. aimagelab/cssl — Code implementation for "Continual Semi-Supervised Learning through Contrastive Interpolation Consistency".
Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning"
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
Implementation of "Overcoming catastrophic forgetting in neural networks" in Tensorflow
Code implementation for "Continual Semi-Supervised Learning through Contrastive Interpolation Consistency"