A simple python library for fast image generation of people who do not exist.

Last update: Dec 15, 2022

Related tags

Deep Learning random_face

Overview

Random Face

A simple python library for fast image generation of people who do not exist.

For more details, please refer to the [paper](https://arxiv.org/abs/2104.04767).

Requirements

Linux, Windows, MacOS
Python 3.8+
CPU compatible with OpenVINO.

Install package

pip install random_face

Install the latest version

git clone https://github.com/bes-dev/random_face.git
cd random_face
pip install -r requirements.txt
python download_model.py
pip install .

Demo

python -m random_face.demo

Example

import cv2
import random_face

engine = random_face.get_engine()
face = engine.get_random_face()
cv2.imshow("face", face)
cv2.waitKey()

Citation

@misc{belousov2021mobilestylegan,
      title={MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis},
      author={Sergei Belousov},
      year={2021},
      eprint={2104.04767},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

You might also like...

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN.

Ryan Murdock has done it again, combining OpenAI's CLIP and the generator from a BigGAN! This repository wraps up his work so it is easily accessible to anyone who owns a GPU.

2.3k Jan 9, 2023

This is the official repo for TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations at CVPR'21. According to some product reasons, we are not planning to release the training/testing codes and models. However, we will release the dataset and the scripts to prepare the dataset.

TransFill-Reference-Inpainting This is the official repo for TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transf

80 Dec 8, 2022

A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

Poisson Image Editing - A Parallel Implementation Jiayi Weng (jiayiwen), Zixu Chen (zixuc) Poisson Image Editing is a technique that can fuse two imag

110 Dec 27, 2022

Python wrappers to the C++ library SymEngine, a fast C++ symbolic manipulation library.

SymEngine Python Wrappers Python wrappers to the C++ library SymEngine, a fast C++ symbolic manipulation library. Installation Pip See License section

136 Dec 28, 2022

Simple-Image-Classification - Simple Image Classification Code (PyTorch)

Simple-Image-Classification Simple Image Classification Code (PyTorch) Yechan Kim This repository contains: Python3 / Pytorch code for multi-class ima

8 Oct 29, 2022

A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding his way.

GuidEye A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding h

0 Aug 9, 2022

Code for "Layered Neural Rendering for Retiming People in Video."

Layered Neural Rendering in PyTorch This repository contains training code for the examples in the SIGGRAPH Asia 2020 paper "Layered Neural Rendering

154 Dec 16, 2022

Implementation for the paper SMPLicit: Topology-aware Generative Model for Clothed People (CVPR 2021)

SMPLicit: Topology-aware Generative Model for Clothed People [Project] [arXiv] License Software Copyright License for non-commercial scientific resear

225 Dec 13, 2022

People movement type classifier with YOLOv4 detection and SORT tracking.

Movement classification The goal of this project would be movement classification of people, in other words, walking (normal and fast) and running. Yo

4 Sep 21, 2021

Comments

Explicitly specified the compatible openvino library version

The latest openvino library 2022.x version is incompatible with this library. Hence updated the requirements file to specify the last compatible version of openvino library. Now the error is fixed and the library is working properly.

More details are in https://github.com/bes-dev/random_face/issues/6
bug

opened by comprakash 3
description of input/ouput of the models

Hi, I've been trying to use the models using another framework, I tried to follow the python code to define de input and output of the two models unsuccessfully.

So far I got:

512 random values > Style model > 512 style values, truncated? > Synthesys model > final image.

Should the random values be between 0 and 1? any additional requirement?

So I need to know the expected values for each input/output, and how to truncate the style values.

opened by vpenades 1
Error: Argument shapes are inconsistent

I am getting an error while trying a simple program. Could you please assist on how to fix this issue.

engine = random_face.get_engine() random_face = engine.get_random_face()

Traceback (most recent call last): File "./scripts/generate_random_fvs.py", line 8, in engine = random_face.get_engine() File "/home/omprakash/github/CassiniServer/venv/lib/python3.8/site-packages/random_face/random_face.py", line 29, in get_engine return EngineOpenvino(cfg) File "/home/omprakash/github/CassiniServer/venv/lib/python3.8/site-packages/random_face/engine_openvino.py", line 39, in init self.snet_exec = self.ie.load_network(network=self.snet, device_name="CPU") File "ie_api.pyx", line 413, in openvino.inference_engine.ie_api.IECore.load_network File "ie_api.pyx", line 457, in openvino.inference_engine.ie_api.IECore.load_network RuntimeError: Check 'PartialShape::broadcast_merge_into(pshape, node->get_input_partial_shape(i), autob)' failed at core/src/op/util/elementwise_args.cpp:30: While validating node 'v1::Multiply Multiply_9566 (Mul_39_copy[0]:f32{512,512,3,3}, Constant_9519[0]:f32{1,512,4,4}) -> (dynamic...)' with friendly_name 'Multiply_9566': Argument shapes are inconsistent.

opened by OmPrakash4 1

how solve this issue?

Processing time: 0.1736280918121338 s.
Press 'q' for quit
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/usr/local/lib/python3.8/dist-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: xcb.

Aborted (core dumped)

opened by johnfelipe 1

Releases(2021.07.21.1)

2021.07.21.1(Jul 21, 2021)

Source code(tar.gz)
Source code(zip)
2021.07.21.0(Jul 21, 2021)
Migrate to new face generation model

Improve FID 12.38 -> 7.75

Source code(tar.gz)
Source code(zip)
2021.04.10.1(Apr 14, 2021)

Source code(tar.gz)
Source code(zip)

Owner

Sergei Belousov

GitHub Repository

Low-code/No-code approach for deep learning inference on devices

EzEdgeAI A concept project that uses a low-code/no-code approach to implement deep learning inference on devices. It provides a componentized framewor

7 Apr 05, 2022

This repository contains code to run experiments in the paper "Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers."

Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers This repository contains code to run experiments in the paper "Signal Stre

0 Jan 19, 2022

Automated Hyperparameter Optimization Competition

QQ浏览器2021AI算法大赛 - 自动超参数优化竞赛 ACM CIKM 2021 AnalyticCup 在信息流推荐业务场景中普遍存在模型或策略效果依赖于“超参数”的问题，而“超参数"的设定往往依赖人工经验调参，不仅效率低下维护成本高，而且难以实现更优效果。因此，本次赛题以超参数优化为主题，从真

20 Dec 09, 2021

Dynamic wallpaper generator.

Wiki • About • Installation About This project is a dynamic wallpaper changer. It waits untill you turn on the music, downloads album cover if it's po

3 Sep 18, 2021

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

FAC-Net Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization Linjiang Huang (CUHK), Liang Wang (CASIA), Hongsheng

21 Nov 22, 2022

AI-generated-characters for Learning and Wellbeing

AI-generated-characters for Learning and Wellbeing Click here for the full project page. This repository contains the source code for the paper AI-gen

214 Jan 01, 2023

Fine-tuning StyleGAN2 for Cartoon Face Generation

Cartoon-StyleGAN 🙃 : Fine-tuning StyleGAN2 for Cartoon Face Generation Abstract Recent studies have shown remarkable success in the unsupervised imag

520 Jan 04, 2023

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation (CoRL 2021)

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation [Project website] [Paper] This project is a PyTorch i

6 Feb 28, 2022

Evolving neural network parameters in JAX.

Evolving Neural Networks in JAX This repository holds code displaying techniques for applying evolutionary network training strategies in JAX. Each sc

6 Feb 12, 2022

Hyperbolic Procrustes Analysis Using Riemannian Geometry

Hyperbolic Procrustes Analysis Using Riemannian Geometry The code in this repository creates the figures presented in this article: Please notice that

2 Jan 08, 2023

Dynamic Graph Event Detection

DyGED Dynamic Graph Event Detection Get Started pip install -r requirements.txt TODO Paper link to arxiv, and how to cite. Twitter Weather dataset tra

3 May 09, 2022

Project page of the paper 'Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network' (ECCVW 2018)

EPSR (Enhanced Perceptual Super-resolution Network) paper This repo provides the test code, pretrained models, and results on benchmark datasets of ou

78 Nov 19, 2022

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

34 Dec 21, 2022

A simple python library for fast image generation of people who do not exist.

Related tags

Overview

Random Face

Requirements

Install package

Install the latest version

Demo

Example

Citation

You might also like...

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN.

A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

Python wrappers to the C++ library SymEngine, a fast C++ symbolic manipulation library.

Simple-Image-Classification - Simple Image Classification Code (PyTorch)

A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding his way.

Code for "Layered Neural Rendering for Retiming People in Video."

Implementation for the paper SMPLicit: Topology-aware Generative Model for Clothed People (CVPR 2021)

People movement type classifier with YOLOv4 detection and SORT tracking.

Comments

Explicitly specified the compatible openvino library version

description of input/ouput of the models

Error: Argument shapes are inconsistent

how solve this issue?

Releases(2021.07.21.1)

2021.07.21.1(Jul 21, 2021)

2021.07.21.0(Jul 21, 2021)

2021.04.10.1(Apr 14, 2021)

Owner

Sergei Belousov

Low-code/No-code approach for deep learning inference on devices

This repository contains code to run experiments in the paper "Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers."

Automated Hyperparameter Optimization Competition

Dynamic wallpaper generator.

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

AI-generated-characters for Learning and Wellbeing

Fine-tuning StyleGAN2 for Cartoon Face Generation

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation (CoRL 2021)

Evolving neural network parameters in JAX.

Hyperbolic Procrustes Analysis Using Riemannian Geometry

Dynamic Graph Event Detection

Project page of the paper 'Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network' (ECCVW 2018)

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Safe Control for Black-box Dynamical Systems via Neural Barrier Certificates

A tutorial on DataFrames.jl prepared for JuliaCon2021

Static Features Classifier - A static features classifier for Point-Could clusters using an Attention-RNN model

KaziText is a tool for modelling common human errors.

Algorithmic encoding of protected characteristics and its implications on disparities across subgroups

PyTorch implementation of paper "IBRNet: Learning Multi-View Image-Based Rendering", CVPR 2021.

Scalable training for dense retrieval models.