Pinned Repositories
ArcFace
虹软的人脸识别V1.2、人证对比、活体检测封装
chinese-idcard-text-renderer
用于生成chinese ocr身份证文本图片
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 , dbnet(1.7M) + crnn(6.3M) + anglenet(1.5M) 总模型仅10M
CPlusPlusThings
C++那些事
datamining
learn in datamining
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
FaceDetect-FaceLandmark
基于ncnn的手机端轻量级人脸检测和关键点定位模型
GPU_Hard_Decode_RTSP
ffmpeg+cuvid硬解码rtsp
RobotVision2
移动端实时疲劳驾驶检测
Try_On_Knowledge_Distillation
A simple try on knowledge distillation.
hzq-zjm's Repositories
hzq-zjm/FaceDetect-FaceLandmark
基于ncnn的手机端轻量级人脸检测和关键点定位模型
hzq-zjm/RobotVision2
移动端实时疲劳驾驶检测
hzq-zjm/GPU_Hard_Decode_RTSP
ffmpeg+cuvid硬解码rtsp
hzq-zjm/Try_On_Knowledge_Distillation
A simple try on knowledge distillation.
hzq-zjm/ArcFace
虹软的人脸识别V1.2、人证对比、活体检测封装
hzq-zjm/chinese-idcard-text-renderer
用于生成chinese ocr身份证文本图片
hzq-zjm/chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 , dbnet(1.7M) + crnn(6.3M) + anglenet(1.5M) 总模型仅10M
hzq-zjm/CPlusPlusThings
C++那些事
hzq-zjm/datamining
learn in datamining
hzq-zjm/DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
hzq-zjm/Face-Detector-1MB-with-landmark
1M人脸检测模型(含关键点)
hzq-zjm/face_landmark
A simple method for face alignment based on wingloss and mutitask learning :)
hzq-zjm/facesample
facesample
hzq-zjm/Hands-on-Machine-Learning
A series of Jupyter notebooks with Chinese comment that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
hzq-zjm/Human-Segmentation-PyTorch
Human segmentation models, training/inference code, and trained weights, implemented in PyTorch
hzq-zjm/lihang-code
《统计学习方法》的代码实现
hzq-zjm/micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
hzq-zjm/modnet_portrait_matting
modnet notes
hzq-zjm/ncnn_example
ncnn example: mask detection: anticonv face detection: retinaface&&mtcnn&¢erface, track: iou tracking, landmark: zqcnn, recognize: mobilefacenet classifier: mobilenet object detecter: mobilenetssd
hzq-zjm/onnx-simplifier
Simplify your onnx model
hzq-zjm/onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
hzq-zjm/pytorch-mobilenet-v2
A PyTorch implementation of MobileNet V2 architecture and pretrained model.
hzq-zjm/pytorch-mobilenet-v3
MobileNetV3 in pytorch and ImageNet pretrained models
hzq-zjm/TensorRT
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
hzq-zjm/tensorrtx
Implementation of popular deep learning networks with TensorRT network definition APIs
hzq-zjm/text-detection-ocr
Chinese text detection and recognition based on CTPN + DENSENET using Keras and Tensor Flow,使用keras和tensorflow基于CTPN+Densenet实现的中文文本检测和识别
hzq-zjm/Try_On_Channel_Pruning
hzq-zjm/Ultra-Light-Fast-Generic-Face-Detector-1MB
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
hzq-zjm/yolov3-channel-and-layer-pruning
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏
hzq-zjm/ZQCNN
一款比mini-caffe更快的Forward库,觉得好用请点星啊,400星公布快速人脸检测模型,500星公布106点landmark,600星公布人头检测模型,700星公布人脸检测套餐(六种pnet,两种rnet随意混合使用满足各种速度/精度要求),800星公布更准的106点模型