baselines Jupyter Notebook

Fork 0 关注 0

OpenAI Baselines 是一个强化学习算法的实现库

原始仓库地址：https://github.com/openai/baselines.git

interpret C++

Fork 0 关注 0

InterpretML是一个开源python软件包，用于训练可解释的机器学习模型，并能解释黑匣子系统

原始仓库地址：https://github.com/interpretml/interpret.git

ai_sudoku Python

Fork 0 关注 0

基于GUI的智能数独求解器，可从图像中提取数独难题并将其解决。

原始仓库地址：https://github.com/neeru1207/ai_sudoku.git

华为方舟计算视觉团队 / PC-DARTS Python

Fork 0 关注 1

PC-DARTS is a memory-efficient differentiable architecture method based on DARTS. It mainly focuses on reducing the large memory cost of the super-net in one-shot NAS method, which means that it can also be combined with other one-shot NAS method e.g. ENAS. Different from previous methods that sampling operations, PC-DARTS samples channels of the constructed super-net. Interestingly, though we introduced randomness during the search process, the performance of the searched architecture is better and more stable than DARTS! For a detailed description of technical details and experimental results, please refer to our paper: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian and Hongkai Xiong. This code is based on the implementation of DARTS.

原始仓库地址：https://github.com/yuhuixu1993/pc-darts.git

华为方舟计算视觉团队 / pdarts Python

Fork 0 关注 1

This repository contains the search and evaluation code for our work Progressive DARTS. It requires only 0.3 GPU-days (7 hours on a single P100 card) to finish a search progress on CIFAR10 and CIFAR100 datasets, much faster than DARTS, and achieves higher classification accuracy on both CIFAR and ImageNet datasets (mobole setting).

原始仓库地址：https://github.com/chenxin061/pdarts.git

华为方舟计算视觉团队 / CenterNet Python

Fork 0 关注 1

CenterNet is a framework for object detection with deep convolutional neural networks. You can use the code to train and evaluate a network for object detection on the MS-COCO dataset. It achieves state-of-the-art performance (an AP of 47.0%) on one of the most challenging dataset: MS-COCO. Our code is written in Python, based on CornerNet. More detailed descriptions of our approach and code will be made available soon. If you encounter any problems in using our code, please contact Kaiwen Duan: kaiwen.duan@vipl.ict.ac.cn.

原始仓库地址：https://github.com/duankaiwen/centernet.git

mcc C++

Fork 0 关注 0

MCC: A scalable and predictable massive network load generator

原始仓库地址：https://github.com/acs-dcn/mcc.git

hcmonitor C

Fork 0 关注 0

HCMonitor is a monitor system for high concurrent network services.

原始仓库地址：https://github.com/acs-dcn/hcmonitor.git

AVS3解码器 C

Fork 1 关注 4

uavs3d是一款全平台覆盖的高性能AVS3解码器，具备以下特性： 1. 对齐HPM4.0参考软件，通过AVS标准组AVS3 H轮符合性测试码流测试。 2. 支持Android/IOS/Windows/Linux/MacOS等系统运行； 3. 针对ARM32/ARM64/X86架构处理器深度优化； 4. 全平台支持高位深(10bits)解码； 5. 支持高效并行解码。

联通智立方 / 人脸识别v3 Python

Fork 0 关注 5

本模型改编自GitHub开源项目：[https://github.com/ageitgey/face_recognition](https://github.com/ageitgey/face_recognition) 鹏城汇智iHub镜像地址：[https://code.ihub.org.cn/projects/338/repository/face_recognition](https://code.ihub.org.cn/projects/338/repository/face_recognition) 本项目的人脸识别是基于业内领先的C++开源库 dlib中的深度学习模型，用Labeled Faces in the Wild人脸数据集进行测试，有高达99.38%的准确率。但对小孩和亚洲人脸的识别准确率尚待提升。 与“人脸识别v2”相比，本项目仅改变了代码结构，将dlib库和预训练人脸识别模型文件等直接打包在程序中，而不需要docker部署后再通过网络进行安装。