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

Benchmark tools for Compressive LiDAR-to-map registration

Face recognition. Redefined.

Companion code for the paper "Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks" by Yatsura et al.

Data visualization app for H&M competition in kaggle

On the Limits of Pseudo Ground Truth in Visual Camera Re-Localization

Task Transformer Network for Joint MRI Reconstruction and Super-Resolution (MICCAI 2021)

[CVPR 2021] Unsupervised 3D Shape Completion through GAN Inversion

Official codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.

Semantic Segmentation for Aerial Imagery using Convolutional Neural Network

Who calls the shots? Rethinking Few-Shot Learning for Audio (WASPAA 2021)

Deep Learning Emotion decoding using EEG data from Autism individuals

Repository for code and dataset for our EMNLP 2021 paper - “So You Think You’re Funny?”: Rating the Humour Quotient in Standup Comedy.

Kohei's 5th place solution for xview3 challenge

Breaking the Dilemma of Medical Image-to-image Translation

A simple Neural Network that predicts the label for a series of handwritten digits

A library for researching neural networks compression and acceleration methods.

Synthesizing Long-Term 3D Human Motion and Interaction in 3D in CVPR2021

Hso-groupie - A pwnable challenge in Real World CTF 4th

Time should be taken seer-iously

Stock-history-display - something like a easy yearly review for your stock performance