Implementation of paper which uses a swish-gated residual U-net to color line-art anime drawings
(5 stars) (3 forks) (0 indexed issues) (0 open good first issues)
Repositories
TachibanaYoshino repositories
A Tensorflow implementation of AnimeGAN for fast photo animation ! This is the Open source of the paper 「AnimeGAN: a novel lightweight GAN for photo animation」, which uses the GAN framwork to transform real-world photos into anime images.
(4,363 stars) (663 forks) (0 indexed issues) (0 open good first issues)
TachibanaYoshino/AnimeGAN.jsJavaScript
AnimeGAN.js: Photo Animation for Everyone
(1 star) (0 forks) (0 indexed issues) (0 open good first issues)
[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime
(4,919 stars) (704 forks) (0 indexed issues) (0 open good first issues)
Implementing AnimeGANv2 with Tensorflow2
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.
(2,019 stars) (263 forks) (0 indexed issues) (0 open good first issues)
The whole image inference based on the onnx model of AnimeGANv3
(27 stars) (4 forks) (0 indexed issues) (0 open good first issues)
The UI tool based on pyqt5 to call the AnimeGANv3 model.
(46 stars) (4 forks) (0 indexed issues) (0 open good first issues)
TachibanaYoshino/GFPGANPython
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
(6 stars) (2 forks) (0 indexed issues) (0 open good first issues)
TachibanaYoshino/NewSeaCity-AI-Media-TransferJupyter Notebook
demo
(0 stars) (0 forks) (0 indexed issues) (0 open good first issues)
OpenPano: Automatic Panorama Stitching From Scratch
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
Based on the DB algorithm of PaddleOCR-2.7, it implements text detection and classification, and supports DB++ algorithm.
(0 stars) (1 fork) (0 indexed issues) (0 open good first issues)
A Cross platform implementation of Wenet ASR inference. It's based on ONNXRuntime and Wenet. We provide a set of easier APIs to call wenet models.
(0 stars) (0 forks) (0 indexed issues) (0 open good first issues)
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
The project uses Unet-based improved networks to study Remote sensing image semantic segmentation, which is based on keras.
(141 stars) (40 forks) (0 indexed issues) (0 open good first issues)
The remote sensing image semantic segmentation repository based on tf.keras includes backbone networks such as resnet, densenet, mobilenet, and segmentation networks such as deeplabv3+, pspnet, panet, and refinenet.
(63 stars) (19 forks) (0 indexed issues) (0 open good first issues)
The project uses Unet-based improved networks to study road crack segmentation, which is based on keras.
(45 stars) (18 forks) (0 indexed issues) (0 open good first issues)
This project is from a kaggle competition in 2016, we use mobileNet V2 to achieve classification recognition based on pytorch.
(7 stars) (2 forks) (0 indexed issues) (0 open good first issues)
(6 stars) (3 forks) (0 indexed issues) (0 open good first issues)
Deep Speaker: an End-to-End Neural Speaker Embedding System.
(0 stars) (0 forks) (0 indexed issues) (0 open good first issues)