PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017

Last update: Dec 14, 2022

Overview

pytorch-deep-generative-replay

PyTorch implementation of Continual Learning with Deep Generative Replay, NIPS 2017

Results

Continual Learning on Permutated MNISTs

Test precisions without replay (left), with exact replay (middle), and with Deep Generative Replay (right).

Continual Learning on MNIST-SVHN

Test precisions without replay (left), with exact replay (middle), and with Deep Generative Replay (right).

Generated samples from the scholar trained without any replay (left) and with Deep Generative Replay (right).

Training scholar's generator without replay (left) and with Deep Generative Replay (right).

Continual Learning on SVHN-MNIST

Test precisions without replay (left), with exact replay (middle), and with Deep Generative Replay (right).

Generated samples from the scholar trained without replay (left) and with Deep Generative Replay (right).

Training scholar's generator without replay (left) and with Deep Generative Replay (right).

Installation

$ git clone https://github.com/kuc2477/pytorch-deep-generative-replay
$ pip install -r pytorch-deep-generative-replay/requirements.txt

Commands

Usage

$ ./main.py --help
$ usage: PyTorch implementation of Deep Generative Replay [-h]
                                                          [--experiment {permutated-mnist,svhn-mnist,mnist-svhn}]
                                                          [--mnist-permutation-number MNIST_PERMUTATION_NUMBER]
                                                          [--mnist-permutation-seed MNIST_PERMUTATION_SEED]
                                                          --replay-mode
                                                          {exact-replay,generative-replay,none}
                                                          [--generator-z-size GENERATOR_Z_SIZE]
                                                          [--generator-c-channel-size GENERATOR_C_CHANNEL_SIZE]
                                                          [--generator-g-channel-size GENERATOR_G_CHANNEL_SIZE]
                                                          [--solver-depth SOLVER_DEPTH]
                                                          [--solver-reducing-layers SOLVER_REDUCING_LAYERS]
                                                          [--solver-channel-size SOLVER_CHANNEL_SIZE]
                                                          [--generator-c-updates-per-g-update GENERATOR_C_UPDATES_PER_G_UPDATE]
                                                          [--generator-iterations GENERATOR_ITERATIONS]
                                                          [--solver-iterations SOLVER_ITERATIONS]
                                                          [--importance-of-new-task IMPORTANCE_OF_NEW_TASK]
                                                          [--lr LR]
                                                          [--weight-decay WEIGHT_DECAY]
                                                          [--batch-size BATCH_SIZE]
                                                          [--test-size TEST_SIZE]
                                                          [--sample-size SAMPLE_SIZE]
                                                          [--image-log-interval IMAGE_LOG_INTERVAL]
                                                          [--eval-log-interval EVAL_LOG_INTERVAL]
                                                          [--loss-log-interval LOSS_LOG_INTERVAL]
                                                          [--checkpoint-dir CHECKPOINT_DIR]
                                                          [--sample-dir SAMPLE_DIR]
                                                          [--no-gpus]
                                                          (--train | --test)

To Run Full Experiments

# Run a visdom server and conduct full experiments
$ python -m visdom.server &
$ ./run_full_experiments

To Run a Single Experiment

# Run a visdom server and conduct a desired experiment
$ python -m visdom.server &
$ ./main.py --train --experiment=[permutated-mnist|svhn-mnist|mnist-svhn] --replay-mode=[exact-replay|generative-replay|none]

To Generate Images from the learned Scholar

$ # Run the command below and visit the "samples" directory
$ ./main.py --test --experiment=[permutated-mnist|svhn-mnist|mnist-svhn] --replay-mode=[exact-replay|generative-replay|none]

Note

I failed to find the supplementary materials that the authors mentioned in the paper to contain the experimental details. Thus, I arbitrarily chose a 4-convolutional-layer CNN as a solver in this project. If you know where I can find the additional materials, please let me know through the project's Github issue.

Reference

Continual Learning with Deep Generative Replay, arxiv:1705.08690

Author

Ha Junsoo / @kuc2477 / MIT License

PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017

Related tags

Overview

pytorch-deep-generative-replay

Results

Continual Learning on Permutated MNISTs

Continual Learning on MNIST-SVHN

Continual Learning on SVHN-MNIST

Installation

Commands

Usage

To Run Full Experiments

To Run a Single Experiment

To Generate Images from the learned Scholar

Note

Reference

Author

Owner

Junsoo Ha

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

DCA - Official Python implementation of Delaunay Component Analysis algorithm

The code repository for "PyCIL: A Python Toolbox for Class-Incremental Learning" in PyTorch.

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation [3DV 2021 Oral]

The UI as a mobile display for OP25

Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

95.47% on CIFAR10 with PyTorch

MetaDrive: Composing Diverse Scenarios for Generalizable Reinforcement Learning

Official Pytorch implementation for video neural representation (NeRV)

Harmonious Textual Layout Generation over Natural Images via Deep Aesthetics Learning

Code for Efficient Visual Pretraining with Contrastive Detection

Global-Local Context Network for Person Search

RADIal is available now! Check the download section

A simple editor for captions in .SRT file extension

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

A PyTorch implementation of "ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning", CIKM-21

A port of muP to JAX/Haiku

Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks

This repository contains the code for the paper Neural RGB-D Surface Reconstruction