j201111100523

-Baseline-

数据科学竞赛各种baseline代码、思路分享

abseil-cpp

Abseil Common Libraries (C++)

ailia-models

The collection of pre-trained, state-of-the-art AI models for ailia SDK

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

CVPR2020-Code

CVPR 2020 论文开源项目合集

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

edusense

EduSense: Practical Classroom Sensing at Scale

face_detect_recognize_ncnn

基于ncnn的人脸识别

facerecognize-for-mobile-phone

适用于移动端的人脸识别模型，计算量与mobilefacenet相同，但megaface上提升了2%+

first-order-model

This repository contains the source code for the paper First Order Motion Model for Image Animation

folly

An open-source C++ library developed and used at Facebook.

Forward

a library for high performance deep learning inference on NVIDIA GPUs.

google-images-download

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

imbalanced-dataset-sampler

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

json-tutorial

从零开始的 JSON 库教程

libfacedetection.train

The training program for libfacedetection for face detection and 5-landmark detection.

nanodet_openvino

手把手教你OpenVINO下部署NanoDet模型，intel i7-7700HQ CPU实测6ms一帧

object-detection-anchors

Tips on how to find suitable object detection anchors

openvino_training_extensions

Trainable models and NN optimization tools

plato

腾讯高性能图计算框架Plato

ppl.nn

A primitive library for neural network

pruning_yolov3

Reading-and-comprehense-linux-Kernel-network-protocol-stack

linux内核网络协议栈源码阅读分析注释--带详尽中文分析注释以及相关流程分析调用注释，对理解分析内核协议栈源码很有帮助

sd-fuse_rk3399

Create bootable SD card for NanoPC-T4/NanoPi M4/NanoPi NEO4

tensorrtx

Implementation of popular deep learning networks with TensorRT network definition API

Ultralight-SimplePose

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

yolo-face-with-landmark

yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测（包含关键点）

Yolo-Fastest

:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB

yolov3-channel-and-layer-pruning

yolov3 channel and layer pruning