Pinned Repositories
chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
context_aug
Context-driven data augmentation for Object Detection (ECCV'18)
Data_Augmentation_Zoo_for_Object_Detection
Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these methods on VOC and KITTI.
EasyQuant
EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.
HyperLandmark
基于深度学习106点人脸标定算法 Open Source Face Landmark
idcardgenerator
身份证图片生成工具 generate an id card picture
kws
An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
learnopencv
Learn OpenCV : C++ and Python Examples
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
ML-KWS-for-MCU
能够在移动端使用的关键词语音识别，其实用的是分类方法来完成的
lxyyang's Repositories
lxyyang/chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
lxyyang/context_aug
Context-driven data augmentation for Object Detection (ECCV'18)
lxyyang/Data_Augmentation_Zoo_for_Object_Detection
Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these methods on VOC and KITTI.
lxyyang/EasyQuant
EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.
lxyyang/HyperLandmark
基于深度学习106点人脸标定算法 Open Source Face Landmark
lxyyang/idcardgenerator
身份证图片生成工具 generate an id card picture
lxyyang/kws
An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
lxyyang/learnopencv
Learn OpenCV : C++ and Python Examples
lxyyang/LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
lxyyang/ML-KWS-for-MCU
能够在移动端使用的关键词语音识别，其实用的是分类方法来完成的
lxyyang/MobileNet-v2-pruning
Try out different pruning-approaches on lightweight Backbones.
lxyyang/model-compression
model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))
lxyyang/ncnnqat
quantize aware training package for NCNN on pytorch
lxyyang/photo2cartoon
人像卡通化探索项目 (photo-to-cartoon translation project)
lxyyang/Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
lxyyang/Semantic-Guided-Low-Light-Image-Enhancement
This is the official Pytorch implementation for our paper "Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement."
lxyyang/SlimYOLOv3
This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications
lxyyang/Stage
工程与学术笔记
lxyyang/Stronger-yolo
Improve yolo with latest paper
lxyyang/unsup-hard-negative-mining-mscoco
Repository for experiments on MSCOCO for Unsupervised Hard Example Mining from Videos for Improved Object Detection(https://arxiv.org/abs/1808.04285)
lxyyang/YOLOv3-complete-pruning
提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。