haopo2005's starred repositories
VIW-Fusion
Visual-inertial-wheel fusion odometry, better performance in scenes with drastic changes in light
Stereo-Odometry-SOFT
MATLAB Implementation of Visual Odometry using SOFT algorithm
dig-into-apollo
Apollo notes (Apollo学习笔记) - Apollo learning notes for beginners.
Deep-Learning-Interview-Book
深度学习面试宝典(含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向)
awesome-canbus
:articulated_lorry: Awesome CAN bus tools, hardware and resources for Cyber Security Researchers, Reverse Engineers, and Automotive Electronics Enthusiasts.
MapGraphics
A tile-based "slippy map" library written in/for C++/Qt. It's meant to enable C++/Qt developers to easily add nice, interactive maps to their applications. Supports zooming, rotating, interactive custom map objects, transparency, etc. It is a Qt map widget that can use tiles from MapQuest, Openstreetmap, or a custom source you define.
qt3d-experiments
Experiments with 3D graphics using Qt3D framework
Deep-Time-Series-Prediction
Seq2Seq, Bert, Transformer, WaveNet for time series prediction.
bert4keras
keras implement of transformers for humans
ladder-latent-data-distribution-modelling
In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We propose LaDDer to achieve accurate modelling of the latent data distribution in a variational autoencoder framework and to facilitate better representation learning. The central idea of LaDDer is a meta-embedding concept, which uses multiple VAE models to learn an embedding of the embeddings, forming a ladder of encodings. We use a non-parametric mixture as the hyper prior for the innermost VAE and learn all the parameters in a unified variational framework. From extensive experiments, we show that our LaDDer model is able to accurately estimate complex latent distribution and results in improvement in the representation quality.
Ensemble-Methods-for-Image-Classification
In this project, I implemented several ensemble methods (including bagging, AdaBoost, SAMME, stacking, snapshot ensemble) for a normal CNN model and Residual Neural Network.
ORB_SLAM2_detailed_comments
Detailed comments for ORB-SLAM2 with trouble-shooting, key formula derivation, and diagrammatic drawing
awesome-visual-slam
:books: The list of vision-based SLAM / Visual Odometry open source, blogs, and papers
PolyLaneNet
Code for the paper entitled "PolyLaneNet: Lane Estimation via Deep Polynomial Regression" (ICPR 2020)
Ultra-Fast-Lane-Detection
Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)
PyTorch-BayesianCNN
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
SimpleAICV_pytorch_training_examples
SimpleAICV:pytorch training and testing examples.
HWCC_image_classification
本赛题任务是对西安的热门景点、美食、特产、民俗、工艺品等图片进行分类,即首先识别出图片中物品的类别(比如大雁塔、肉夹馍等),然后根据图片分类的规则,输出该图片中物品属于景点、美食、特产、民俗和工艺品中的哪一种。
RegNet-Search-PyTorch
Search for RegNet using PyTorch