hongbowei Goto Github PK

daily-paper-computer-vision

记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

darknet

darknet深度学习框架源码分析：详细中文注释，涵盖框架原理与实现语法分析

data-driven-pdes

datawhale_learning

Datawhale_Learning涵盖了AI领域从理论知识到动手实践的学习内容

deep-learning-localization-mapping

A collection of deep learning based localization models

deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

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15个章节，近20万字。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[email protected] 版权所有，违权必究 Tan 2018.06

deeplearning_ai_books

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

deeplearningbook-chinese

Deep Learning Book Chinese Translation

denoise-imu-gyro

Convolutional Neural Networks for Denoising Gyroscopes of Low-Cost IMUs

dense_flow

OpenCV Implementation of different optical flow algorithms

depth-vo-feat

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

distance-estimation-and-depth-map-creation-using-opencv

In this day and age, when google cars and tesla’s autopilot features are becoming more mainstream, combined with the huge advances in machine learning and computer vision. It has become more important for us to understand and learn the fundamental and basic steps of computer vision. The purpose of this project is to identify a method of image processing that can then be used to develop a software tool. The tool itself will be used to work out the distance that certain objects are away from it using stereo vision. This tool will also allow the user to calibrate the cameras and take both pictures and videos. The hardware used in this project will be low-end but the steps and methods used should be easily transferable and usable with most equipment.

dive-into-dl-pytorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

doxa

A Local Adaptive Thresholding framework for image binarization written in C++, with WASM support. Implementing: Otsu, Bernsen, Niblack, Sauvola, Wolf, Gatos, NICK, Su, T.R. Singh, WAN, ISauvola, Bataineh and Shafait.

dpm

Deformable Part-based Model for Windows

ds-cheatsheets

List of Data Science Cheatsheets to rule the world

dslam_open

Public code for "Data-Efficient Decentralized Visual SLAM"

dso

Direct Sparse Odometry

dso_ros

ROS wrapper for dso

edvr

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks

elsd

Ellipse and Segment Line Detector

elsdc

Ellipse and Line Segment Detector, with Continuous validation

enresnet

ethzasl_msf

MSF - Modular framework for multi sensor fusion based on an Extended Kalman Filter (EKF)

eval-vislam

Toolkit for VI-SLAM evaluation.

event_feature_tracking

This repo contains MATLAB implementations of the event-based feature tracking methods described in "Event-based Feature Tracking with Probabilistic Data Association" and "Event-based Visual Inertial Odometry".

evision

计算机视觉实践和探索/Practice and explorations in computer vision.

evo

Python package for the evaluation of odometry and SLAM