maxuehao Goto Github PK

arcface-caffe

insightface-caffe

autokeras

This is an example of using AutoKeras on image classification issues.

autokeras-1

accessible AutoML for deep learning.

caffe

Add yolov3 upsampler layer

caffe-face

This branch is developed for deep face recognition

caffe-mobilenet-v3

Caffe Implementation of MobileNets V3

cocodata_yolo_train

coco2017数据集官方json标签文件转yolo训练的txt标签文件

crossstagepartialnetworks

Cross Stage Partial Networks

darknet

Convolutional Neural Networks

darknet_face_with_landmark

加入关键点的darknet训练框架，轻量级的人脸检测，支持ncnn推理

deep-residual-networks

Deep Residual Learning for Image Recognition

densenet-caffe

DenseNet Caffe Models, converted from https://github.com/liuzhuang13/DenseNet

dynamic-face-recognition

Deep learning,Face recognition algorithm based on Mobilenet and Mtcnn(LFW 99.1%, Mobilenet-based face recognition model is superior to the accuracy of the original centerloss paper)

face-detector-1mb-with-landmark

1M人脸检测模型(含关键点)

fastestdet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 30% compared with yolo-fastest, and the post-processing is simpler

flashcache

A general purpose, write-back block cache for Linux.

incubator-mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

insightface

Face Analysis Project on MXNet

largemargin_softmax_loss

Implementation for <Large-Margin Softmax Loss for Convolutional Neural Networks> in ICML'16.

mobileface

A face recognition solution on mobile device.

mobilenet-caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

mobilenet-ssd

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

mobilenet-yolo

A caffe implementation of MobileNet-YOLO detection network

mobilenetv2-ssdlite

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

mobilenetv2-yolov3

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops500KB:fire::fire::fire:

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

py_lstm

Lstm前推底层运算

python-

python-script

python