Official implementation of Densely connected normalizing flows

Last update: Dec 12, 2022

Related tags

Overview

Densely connected normalizing flows

This repository is the official implementation of NeurIPS 2021 paper Densely connected normalizing flows. Poster available here.

Setup

CUDA 11.1
Python 3.8

pip install -r requirements.txt
pip install -e .

Training

cd ./experiments/image

CIFAR-10:

python train.py --epochs 400 --batch_size 64 --optimizer adamax --lr 1e-3  --gamma 0.9975 --warmup 5000  --eval_every 1 --check_every 10 --dataset cifar10 --augmentation eta --block_conf 6 4 1 --layers_conf  5 6 20  --layer_mid_chnls 48 48 48 --growth_rate 10  --name DF_74_10

python train_more.py --model ./log/cifar10_8bit/densenet-flow/expdecay/DF_74_10 --new_lr 2e-5 --new_epochs 420

ImageNet32:

python train.py --epochs 20 --batch_size 64 --optimizer adamax --lr 1e-3  --gamma 0.95 --warmup 5000  --eval_every 1 --check_every 10 --dataset imagenet32 --augmentation eta --block_conf 6 4 1 --layers_conf  5 6 20  --layer_mid_chnls 48 48 48 --growth_rate 10  --name DF_74_10

python train_more.py --model ./log/imagenet32_8bit/densenet-flow/expdecay/DF_74_10 --new_lr 2e-5 --new_epochs 22

ImageNet64:

python train.py --epochs 10 --batch_size 32 --optimizer adamax --lr 1e-3  --gamma 0.95 --warmup 5000  --eval_every 1 --check_every 10 --dataset imagenet64 --augmentation eta --block_conf 6 4 1 --layers_conf  5 6 20  --layer_mid_chnls 48 48 48 --growth_rate 10  --name DF_74_10

python train_more.py --model ./log/imagenet64_8bit/densenet-flow/expdecay/DF_74_10 --new_lr 2e-5 --new_epochs 11

CelebA:

python train.py --epochs 50 --batch_size 32 --optimizer adamax --lr 1e-3  --gamma 0.95 --warmup 5000  --eval_every 1 --check_every 10 --dataset celeba --augmentation horizontal_flip --block_conf 6 4 1 --layers_conf  5 6 20  --layer_mid_chnls 48 48 48 --growth_rate 10  --name DF_74_10

python train_more.py --model ./log/celeba_8bit/densenet-flow/expdecay/DF_74_10 --new_lr 2e-5 --new_epochs 55

Note: Download instructions for ImageNet and CelebA are defined in denseflow/data/datasets/image/{dataset}.py

Evaluation

CIFAR-10:

python eval_loglik.py --model PATH_TO_MODEL --k 1000 --kbs 50

ImageNet32:

python eval_loglik.py --model PATH_TO_MODEL --k 200 --kbs 50

ImageNet64 and CelebA:

python eval_loglik.py --model PATH_TO_MODEL --k 200 --kbs 25

Model weights

Model weights are stored here.

Samples generation

Generated samples are stored in PATH_TO_MODEL/samples

python eval_sample.py --model PATH_TO_MODEL

Note: PATH_TO_MODEL has to contain check directory.

ImageNet 32x32

ImageNet 64x64

CelebA

Acknowledgements

Significant part of this code benefited from SurVAE [1] code implementation, available under MIT license.

References

[1] Didrik Nielsen, Priyank Jaini, Emiel Hoogeboom, Ole Winther, and Max Welling. Survae flows: Surjections to bridge the gap between vaes and flows. InAdvances in Neural Information Processing Systems 33. Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020.

Official implementation of Densely connected normalizing flows

Related tags

Overview

Densely connected normalizing flows

Setup

Training

Evaluation

Model weights

Samples generation

ImageNet 32x32

ImageNet 64x64

CelebA

Acknowledgements

References

Owner

Matej Grcić

make ASCII Art by Deep Learning

Signals-backend - A suite of card games written in Python

Speech recognition tool to convert audio to text transcripts, for Linux and Raspberry Pi.

An educational tool to introduce AI planning concepts using mobile manipulator robots.

CONetV2: Efficient Auto-Channel Size Optimization for CNNs

Unofficial Tensorflow-Keras implementation of Fastformer based on paper [Fastformer: Additive Attention Can Be All You Need](https://arxiv.org/abs/2108.09084).

Implementation of Wasserstein adversarial attacks.

Instant Real-Time Example-Based Style Transfer to Facial Videos

Code base for "On-the-Fly Test-time Adaptation for Medical Image Segmentation"

mmdetection version of TinyBenchmark.

PyTorch implementation of MSBG hearing loss model and MBSTOI intelligibility metric

ML-Ensemble – high performance ensemble learning

ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure

Implementation of OpenAI paper with Simple Noise Scale on Fastai V2

[CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment

Run PowerShell command without invoking powershell.exe

Optimizers-visualized - Visualization of different optimizers on local minimas and saddle points.

Replication Package for "An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets"

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks