A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch

Overview

A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch

The official pytorch implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis", the paper can be found here.

0. Data

The datasets used in the paper can be found at link.

After testing on over 20 datasets with each has less than 100 images, this GAN converges on 80% of them. I still cannot summarize an obvious pattern of the "good properties" for a dataset which this GAN can converge on, please feel free to try with your own datasets.

1. Description

The code is structured as follows:

  • models.py: all the models' structure definition.

  • operation.py: the helper functions and data loading methods during training.

  • train.py: the main entry of the code, execute this file to train the model, the intermediate results and checkpoints will be automatically saved periodically into a folder "train_results".

  • eval.py: generates images from a trained generator into a folder, which can be used to calculate FID score.

  • benchmarking: the functions we used to compute FID are located here, it automatically downloads the pytorch official inception model.

  • lpips: this folder contains the code to compute the LPIPS score, the inception model is also automatically download from official location.

  • scripts: this folder contains many scripts you can use to play around the trained model. Including:

    1. style_mix.py: style-mixing as introduced in the paper;
    2. generate_video.py: generating a continuous video from the interpolation of generated images;
    3. find_nearest_neighbor.py: given a generated image, find the closest real-image from the training set;
    4. train_backtracking_one.py: given a real-image, find the latent vector of this image from a trained Generator.

2. How to run

Place all your training images in a folder, and simply call

python train.py --path /path/to/RGB-image-folder

You can also see all the training options by:

python train.py --help

The code will automatically create a new folder (you have to specify the name of the folder using --name option) to store the trained checkpoints and intermediate synthesis results.

Once finish training, you can generate 100 images (or as many as you want) by:

cd ./train_results/name_of_your_training/
python eval.py --n_sample 100 

3. Pre-trained models

The pre-trained models and the respective code of each model are shared here.

You can also use FastGAN to generate images with a pre-packaged Docker image, hosted on the Replicate registry: https://beta.replicate.ai/odegeasslbc/FastGAN

4. Important notes

  1. The provided code is for research use only.

  2. Different model and training configurations are needed on different datasets. You may have to tune the hyper-parameters to get the best results on your own datasets.

    2.1. The hyper-parameters includes: the augmentation options, the model depth (how many layers), the model width (channel numbers of each layer). To change these, you have to change the code in models.py and train.py directly.

    2.2. Please check the code in the shared pre-trained models on how each of them are configured differently on different datasets. Especially, compare the models.py for ffhq and art datasets, you will get an idea on what chages could be made on different datasets.

5. Other notes

  1. The provided scripts are not well organized, contributions are welcomed to clean them.
  2. An third-party implementation of this paper can be found here, where some other techniques are included. I suggest you try both implementation if you find one of them does not work.
Owner
Bingchen Liu
Bingchen Liu
Picasso: a methods for embedding points in 2D in a way that respects distances while fitting a user-specified shape.

Picasso Code to generate Picasso embeddings of any input matrix. Picasso maps the points of an input matrix to user-defined, n-dimensional shape coord

Pachter Lab 45 Dec 23, 2022
Fashion Recommender System With Python

Fashion-Recommender-System Thr growing e-commerce industry presents us with a la

Omkar Gawade 2 Feb 02, 2022
A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

this is a simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

crispengari 5 Dec 09, 2021
This is the official implementation of "One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval".

CORA This is the official implementation of the following paper: Akari Asai, Xinyan Yu, Jungo Kasai and Hannaneh Hajishirzi. One Question Answering Mo

Akari Asai 59 Dec 28, 2022
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

ImageNet-21K Pretraining for the Masses Paper | Pretrained models Official PyTorch Implementation Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, Lihi Zelni

574 Jan 02, 2023
K-FACE Analysis Project on Pytorch

Installation Setup with Conda # create a new environment conda create --name insightKface python=3.7 # or over conda activate insightKface #install t

Jung Jun Uk 7 Nov 10, 2022
Deep Semisupervised Multiview Learning With Increasing Views (IEEE TCYB 2021, PyTorch Code)

Deep Semisupervised Multiview Learning With Increasing Views (ISVN, IEEE TCYB) Peng Hu, Xi Peng, Hongyuan Zhu, Liangli Zhen, Jie Lin, Huaibai Yan, Dez

3 Nov 19, 2022
Code for Referring Image Segmentation via Cross-Modal Progressive Comprehension, CVPR2020.

CMPC-Refseg Code of our CVPR 2020 paper Referring Image Segmentation via Cross-Modal Progressive Comprehension. Shaofei Huang*, Tianrui Hui*, Si Liu,

spyflying 55 Dec 01, 2022
Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Paddle-Adversarial-Toolbox Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle. Model Zoo Common FGS

AgentMaker 17 Nov 08, 2022
Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.

CSE-Autoloss Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models

Peidong Liu(εˆ˜ζ²›δΈœ) 54 Dec 17, 2022
Code for our WACV 2022 paper "Hyper-Convolution Networks for Biomedical Image Segmentation"

Hyper-Convolution Networks for Biomedical Image Segmentation Code for our WACV 2022 paper "Hyper-Convolution Networks for Biomedical Image Segmentatio

Tianyu Ma 17 Nov 02, 2022
ivadomed is an integrated framework for medical image analysis with deep learning.

Repository on the collaborative IVADO medical imaging project between the Mila and NeuroPoly labs.

144 Dec 19, 2022
Generative Flow Networks for Discrete Probabilistic Modeling

Energy-based GFlowNets Code for Generative Flow Networks for Discrete Probabilistic Modeling by Dinghuai Zhang, Nikolay Malkin, Zhen Liu, Alexandra Vo

Narsil-Dinghuai Zhang 51 Dec 20, 2022
Official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence".

The DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergen

281 Dec 30, 2022
Waymo motion prediction challenge 2021: 3rd place solution

Waymo motion prediction challenge 2021: 3rd place solution πŸ“œ Technical report πŸ—¨οΈ Presentation πŸŽ‰ Announcement πŸ›†Motion Prediction Channel Website πŸ›†

158 Jan 08, 2023
PyTorch implementations of the beta divergence loss.

Beta Divergence Loss - PyTorch Implementation This repository contains code for a PyTorch implementation of the beta divergence loss. Dependencies Thi

Billy Carson 7 Nov 09, 2022
FaRL for Facial Representation Learning

FaRL for Facial Representation Learning This repo hosts official implementation of our paper General Facial Representation Learning in a Visual-Lingui

Microsoft 19 Jan 05, 2022
Lava-DL, but with PyTorch-Lightning flavour

Deep learning project seed Use this seed to start new deep learning / ML projects. Built in setup.py Built in requirements Examples with MNIST Badges

Sami BARCHID 4 Oct 31, 2022
StarGAN2 for practice

StarGAN2 for practice This version of StarGAN2 (coined as 'Post-modern Style Transfer') is intended mostly for fellow artists, who rarely look at scie

vadim epstein 87 Sep 24, 2022
It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

CLIP-ONNX It is a simple library to speed up CLIP inference up to 3x (K80 GPU) Usage Install clip-onnx module and requirements first. Use this trick !

Gerasimov Maxim 93 Dec 20, 2022