Robin Wong's repositories
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
color_calibration
color calibration
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
sssegmentation
sssegmentation is a general framework for our research on strongly supervised semantic segmentation.
tongue_recognization_based_on_tensorflow_object_detection_api
fine-tune models like ssd_mobilenet、faster_rcnn models in COCO dataset
FDU-TC
Tongue Crack Image Dataset
AnimeGANv2
[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime
ALAE
[CVPR2020] Adversarial Latent Autoencoders
first-order-model
This repository contains the source code for the paper First Order Motion Model for Image Animation
traditional_Chinese_medicine
大创项目：中医药知识图谱构建
tensorflow-yolov4-tflite
YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
scalismo-faces
Scalable Image Analysis and Shape Modelling: Module to work with 2d images, with a focus on face images
chineseocr
yolo3+ocr
ChineseSemanticKB
ChineseSemanticKB,chinese semantic knowledge base, 面向中文处理的12类、百万规模的语义常用词典，包括34万抽象语义库、34万反义语义库、43万同义语义库等，可支持句子扩展、转写、事件抽象与泛化等多种应用场景。
DeepNude-an-Image-to-Image-technology
DeepNude's algorithm and general image generation theory and practice research, including pix2pix, CycleGAN, UGATIT, DCGAN, SinGAN, ALAE, mGANprior, StarGAN-v2 and VAE models (TensorFlow2 implementation). DeepNude的算法以及通用生成对抗网络（GAN,Generative Adversarial Network）图像生成的理论与实践研究。
roLabelImg
Label Rotated Rect On Images for training
pix2pixHD
Synthesizing and manipulating 2048x1024 images with conditional GANs
DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
DeepSpeech-examples
Examples of how to use or integrate DeepSpeech
style2paints
sketch + style = paints :art: (TOG2018/SIGGRAPH2018ASIA)
ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
threejs-miniprogram
WeChat MiniProgram adapted version of Three.js
you-get
:arrow_double_down: Dumb downloader that scrapes the web
albert_zh
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
faceai
一款入门级的人脸、视频、文字检测以及识别的项目.
ConSinGAN
Official PyTorch implementation of "Improved Techniques for Training Single-Image GANs"
AnimeGAN
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.
halo
✍ An excellent open source blog publishing application. | 一个优秀的开源博客发布应用。