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

Image data augmentation scheduler for albumentations transforms

Machine Learning in Asset Management (by @firmai)

EdiBERT is a generative model based on a bi-directional transformer, suited for image manipulation

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

Code for Overinterpretation paper Overinterpretation reveals image classification model pathologies

A Learning-based Camera Calibration Toolbox

Human annotated noisy labels for CIFAR-10 and CIFAR-100.

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers.

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

Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR18, PAMI19)

Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation

Image Captioning using CNN and Transformers

Context-Sensitive Misspelling Correction of Clinical Text via Conditional Independence, CHIL 2022

Unit-Convertor - Unit Convertor Built With Python

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

Datasets and source code for our paper Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach

Using LSTM to detect spoofing attacks in an Air-Ground network

Comp445 project - Data Communications & Computer Networks

Specificity-preserving RGB-D Saliency Detection