scangit

arrayfire

CenterFace

face detection

CenterFace.pytorch

unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection

CenterMulti

基于CenterNet训练的目标检测&人脸对齐&姿态估计模型

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

CRNN_Tensorflow

Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition

datasets-preprocessing-for-object-detection

this repository includes some python parser scripts for converting other public datasets into voc data format

EasyQuant

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

FairMOT

A simple baseline for one-shot multi-object tracking

keras-lbl-IvS

keras实现人证比对论文《Large-scale Bisample Learning on ID vs. Spot Face Recognition》的核心**; 当类别数非常大时(超过百万)，GPU显存可能无法装载权重参数；可以使用支配原型概念，每个step将相关的类别一块训练，step开始时将当前mini-batch的类别原型权重加载到GPU中，而不用加载所有的类别权重参数; step结束时更新并保存当前训练类别的原型权重

scangit/arrayfire

scangit/CenterFace

face detection

scangit/CenterFace.pytorch

unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection

scangit/CenterMulti

基于CenterNet训练的目标检测&人脸对齐&姿态估计模型

scangit/CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

scangit/CRNN_Tensorflow

Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition

scangit/datasets-preprocessing-for-object-detection

this repository includes some python parser scripts for converting other public datasets into voc data format

scangit/EasyQuant

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

scangit/FairMOT

A simple baseline for one-shot multi-object tracking

scangit/keras-lbl-IvS

keras实现人证比对论文《Large-scale Bisample Learning on ID vs. Spot Face Recognition》的核心**; 当类别数非常大时(超过百万)，GPU显存可能无法装载权重参数；可以使用支配原型概念，每个step将相关的类别一块训练，step开始时将当前mini-batch的类别原型权重加载到GPU中，而不用加载所有的类别权重参数; step结束时更新并保存当前训练类别的原型权重

scangit/Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

scangit/mnist_fakequantization

mnist_fakequantization

scangit/NDK_OpenGLES_3_0

Android OpenGL ES 3.0 从入门到精通系统性学习教程

scangit/neural-network-transpiler

Deep neural network inference transpiler tool for tflite and NNAPI

scangit/onnx-simplifier

Simplify your onnx model

scangit/onnx-utils

Utility scripts for editing or modifying onnx models

scangit/onnx2caffe

onnx模型转caffe模型的工具

scangit/PyNET

Generating RGB photos from RAW image files with PyNET

scangit/pytorch-retinanet

Pytorch implementation of RetinaNet object detection.

scangit/qnx-gles-tutorials

OpenGL ES 2.0 Tutorials on QNX

scangit/QNX_Driver

This simple project demonstrates the functionality of an IO driver, being used as a resource manager.

scangit/rk-datasheet

rk-datasheet

scangit/rk-document

rk-document

scangit/rk-open-docs

internal docs

scangit/rknn-toolkit

scangit/rknpu

scangit/start-machine-learning

A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2021 without ANY background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

scangit/ThreeDPoseUnitySample

Unity sample of 3D pose estimation

scangit/yolov5

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

scangit/YOLOv5_NCNN

🍅 Ncnn deployment on mobile,support:YOLOv5s,YOLOv4-tiny,MobileNetV2-YOLOv3-nano,Simple-Pose,Yolact,ChineseOCR-lite,ENet and Landmark106 on camera.