lxyyang

Xieyangyang's repositories

chinese_ocr

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

Language:PythonApache-2.0010

context_aug

Context-driven data augmentation for Object Detection (ECCV'18)

Language:Jupyter NotebookMIT010

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.

Language:Python000

EasyQuant

EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.

Language:PythonNOASSERTION000

HyperLandmark

基于深度学习106点人脸标定算法 Open Source Face Landmark

Language:C++Apache-2.0010

idcardgenerator

身份证图片生成工具 generate an id card picture

Language:PythonGPL-3.0000

kws

An End-to-End Architecture for Keyword Spotting and Voice Activity Detection

Language:PythonMIT010

learnopencv

Learn OpenCV : C++ and Python Examples

Language:Jupyter Notebook010

LightNet

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

Language:PythonMIT010

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

Language:Objective-CApache-2.0010

MobileNet-v2-pruning

Try out different pruning-approaches on lightweight Backbones.

Language:Python000

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))

Language:Python000