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

3D-Reconstruction 基于深度学习方法的单目多视图三维重建

Notes taking website build with Docker + Django + React.

[CVPR'2020] DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data

This project intends to use SVM supervised learning to determine whether or not an individual is diabetic given certain attributes.

Learning Skeletal Articulations with Neural Blend Shapes

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Recurrent Neural Network Tutorial, Part 2 - Implementing a RNN in Python and Theano

A developer interface for creating Chat AIs for the Chai app.

Neural Scene Graphs for Dynamic Scene (CVPR 2021)

PyTorch implementation of our paper: Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition

CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images

PHOTONAI is a high level python API for designing and optimizing machine learning pipelines.

VD-BERT: A Unified Vision and Dialog Transformer with BERT

A library for uncertainty quantification based on PyTorch

Investigating Attention Mechanism in 3D Point Cloud Object Detection (arXiv 2021)

Spherical Confidence Learning for Face Recognition, accepted to CVPR2021.

CVNets: A library for training computer vision networks

PyTorch code for the NAACL 2021 paper "Improving Generation and Evaluation of Visual Stories via Semantic Consistency"

MicRank is a Learning to Rank neural channel selection framework where a DNN is trained to rank microphone channels.

SAFL: A Self-Attention Scene Text Recognizer with Focal Loss