GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → VITA-Group → GAN-LTH

VITA-Group / GAN-LTH

Licence: MIT license
[ICLR 2021] "GANs Can Play Lottery Too" by Xuxi Chen, Zhenyu Zhang, Yongduo Sui, Tianlong Chen

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

transfergenerative-adversarial-networkganpruninglottery-ticket-hypothesis

Projects that are alternatives of or similar to GAN-LTH

Neuralnetworks.thought Experiments
Observations and notes to understand the workings of neural network models and other thought experiments using Tensorflow
Stars: ✭ 199 (+729.17%)
Mutual labels:  generative-adversarial-network, pruning
Generalizing-Lottery-Tickets
This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"
Stars: ✭ 48 (+100%)
Mutual labels:  pruning, lottery-ticket-hypothesis
precision-recall-distributions
Assessing Generative Models via Precision and Recall (official repository)
Stars: ✭ 80 (+233.33%)
Mutual labels:  generative-adversarial-network
HashGAN
HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
Stars: ✭ 63 (+162.5%)
Mutual labels:  generative-adversarial-network
MultiGraphGAN
MultiGraphGAN for predicting multiple target graphs from a source graph using geometric deep learning.
Stars: ✭ 16 (-33.33%)
Mutual labels:  generative-adversarial-network
CycleGAN-gluon-mxnet
this repo attemps to reproduce Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks(CycleGAN) use gluon reimplementation
Stars: ✭ 31 (+29.17%)
Mutual labels:  generative-adversarial-network
prunnable-layers-pytorch
Prunable nn layers for pytorch.
Stars: ✭ 47 (+95.83%)
Mutual labels:  pruning
SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)
Stars: ✭ 118 (+391.67%)
Mutual labels:  generative-adversarial-network
Paper-Notes
Paper notes in deep learning/machine learning and computer vision
Stars: ✭ 37 (+54.17%)
Mutual labels:  generative-adversarial-network
publications-arruda-ijcnn-2019
Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night
Stars: ✭ 59 (+145.83%)
Mutual labels:  generative-adversarial-network
FAST-RIR
This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
Stars: ✭ 90 (+275%)
Mutual labels:  generative-adversarial-network
just-drop-it
Simply and instantly beam a file between two browsers
Stars: ✭ 22 (-8.33%)
Mutual labels:  transfer
deep-blueberry
If you've always wanted to learn about deep-learning but don't know where to start, then you might have stumbled upon the right place!
Stars: ✭ 17 (-29.17%)
Mutual labels:  generative-adversarial-network
Anime2Sketch
A sketch extractor for anime/illustration.
Stars: ✭ 1,623 (+6662.5%)
Mutual labels:  generative-adversarial-network
mtss-gan
MTSS-GAN: Multivariate Time Series Simulation with Generative Adversarial Networks (by @firmai)
Stars: ✭ 77 (+220.83%)
Mutual labels:  generative-adversarial-network
speech-enhancement-WGAN
speech enhancement GAN on waveform/log-power-spectrum data using Improved WGAN
Stars: ✭ 35 (+45.83%)
Mutual labels:  generative-adversarial-network
30-Days-GANs-Paper-Reading
30 Days GANs Paper Reading
Stars: ✭ 41 (+70.83%)
Mutual labels:  generative-adversarial-network
pytorch-gans
PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN
Stars: ✭ 21 (-12.5%)
Mutual labels:  generative-adversarial-network
Generative MLZSL
[TPAMI Under Submission] Generative Multi-Label Zero-Shot Learning
Stars: ✭ 37 (+54.17%)
Mutual labels:  generative-adversarial-network
gans-2.0
Generative Adversarial Networks in TensorFlow 2.0
Stars: ✭ 76 (+216.67%)
Mutual labels:  generative-adversarial-network
View All Similar Projects ➔

GANs Can Play Lottery Tickets Too

License: MIT

Code for this paper GANs Can Play Lottery Tickets Too.

Overview

For a range of GANs, we can find matching subnetworks at 67%-74% sparsity. We observe that with or without pruning discriminator has a minor effect on the existence and quality of matching subnetworks, while the initialization used in the discriminator plays a significant role.

Experiment Results

Iterative pruning results on SNGAN

Requirements

pytorch==1.4.0 tensorflow-gpu=1.15.0 imageio scikit-image tqdm tensorboardx

Command

SNGAN

Generate Initial Weights

mkdir initial_weights
python generate_initial_weights.py --model sngan_cifar10

Prepare FID statistics

Download FID statistics files from here to fid_stat.

Baseline

python train.py --model sngan_cifar10 --exp_name sngan_cifar10 --init-path initial_weights

Baseline models are also available here.

Iterative Magnitude Pruning on Generator (IMPG)

python train_impg.py --model sngan_cifar10 --exp_name sngan_cifar10 --init-path initial_weights --load-path <path/to/log>

Iterative Magnitude Pruning on Generator (IMPGD)

python train_impgd.py --model sngan_cifar10 --exp_name sngan_cifar10 --init-path initial_weights

Iterative Magnitude Pruning on Generator (IMPGDKD)

python train_impgd.py --model sngan_cifar10 --exp_name sngan_cifar10 --init-path initial_weights --use-kd-d

CycleGAN

Generate initial weights

mkdir initial_weights
python generate_initial_weights.py

Download Data

./download_dataset DATASET_NAME

Baseline

python train.py --dataset DATASET_NAME --rand initial_weights --gpu GPU

IMPG

python train_impg.py --dataset DATASET_NAME --rand initial_weights --gpu GPU --pretrain PRETRAIN

IMPGD

python train_impg.py --dataset DATASET_NAME --rand initial_weights --gpu GPU --pretrain PRETRAIN

Acknowledgement

Inception Score code from OpenAI's Improved GAN (official), and the FID code and CIFAR-10 statistics file from https://github.com/bioinf-jku/TTUR (official).

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].