Toggle navigation
Rico's Nerd Cluster
Home
About
Archive
Archive
「我干了什么 究竟拿了时间换了什么」
Show All
125
Deep Learning
62
C++
12
Math
11
Python
8
RGBD Slam
8
Computer Vision
7
Robotics
6
Hands-on
5
Linux
5
ROS2
5
ROS
4
CUDA
2
Hands-On
2
Classical Machine Learning
1
Data Management
1
Docker
1
Git
1
OpenCV
1
2024
Robotics General Design Notes
What's New In ROS2
Robotics - ROS2 Basic Pub Sub Node
ROS2 Basics
Robotics - ROS2 Gazebo Differential Drive Onboard
ROS2, Gazebo
Robotics - Differences and Similarities Between ROS1 & ROS2
What's New In ROS2
Robotics - 2024 3D Lidar Selection For Robotics
Livox, Unitree Lidars
RGBD SLAM - Amazon SageMaker Usage Notes
Amazon SageMaker, EC2 Instances
RGBD SLAM - GPU Setup
Summary Of Nvidia Orin Nano Setup, Docker For General Machine Learning
RGBD SLAM - Building A ROS 2 Docker Container For Object Detection
ROS 2 Docker Container For Object Detection Training And Inferencing
RGBD SLAM - What Deteriorates Its Performance
Lessons Learned From My RGBD SLAM Project. Updates Come In Anytime
RGBD SLAM Bundle Adjustment Part 2
RGBD SLAM Backend Introduction
RGBD SLAM - Bundle Adjustment From Zero To Hero, Part 1, Theories
RGBD SLAM Backend Introduction
RGBD SLAM - The PnP Problem
Solving the PnP problem - turning pixels into 3D positions!
More On Motion Estimation
5 Point Algorithm, How to solve DLT, and 8 point algorithm
Motion Estimation From Epipolar Constraints
This is an Introduction of Epipolar Constraints and 2D-2D Motion Estimation
C++ - Writing GTest for ROS
Test! Test! Test!
OpenCV and Eigen Tools
A Running List of Opencv and Eigen Tools
Docker Tools
This blog is a collection of Facts about Docker that I found useful
ROS Infrastructure Notes
A Running List of ROS Infrastructure I found Useful
Robotics Fundamentals - Rotations
Getting back to the fundamentals? Let's roll with rotations
2023
CMake - Storing Data on Google Drive
Google Drive
CMake - Concepts and Options
A Running List of CMake Thingamagigs
My Journey Into CUDA
Various things about CUDA that I learned...
Bash Magic
Bash is great. Here is a list of bash tricks & knowledge points that I found magical
ROS - Using GDB for ROS
GDB is a very useful that allows us to pause at a break point or failure and inspect.
ROS Infrastructure Notes
A Running List of ROS Infrastructure I found Useful
C++ - Linkage
In C++, Linkage is Either External Or Internal
C++ - Static Functions And Keyword
Static Functions And Keyword
C++ - Container Operations
Vector, Map, Algorithms
C++ - BLAS and LAPACK
Scientific Computing Libraries
C++ - Casting
Ever tried convincing your boss that your need for vacation is a 'const' by using const_cast? Welcome to C++ casting!
C++ - Bit Operations
A Mumbo Jumbo List About Bit and Byte Operations
C++ - Erase Remove
An efficient in-place way to remove elements in a container
C++ - Weird & Interesting Stuff I found
Oh boy, C++ is weird ... but also interesting :)
C++ - Virtual Functions and Virtual Inheritance
Virtual is virtually complicated. Dynamic Dispatch, Dreadful Diamond Derivative (DDD) Problem ...
C++ - Useful Macros
Why do we still need macros for C++? Please click in and take a look!
2022
Deep Learning - Spatial Pyramid Pooling
SPP, Ablation Study
Deep Learning - Deeplab Series Theories
Deeplab, ASPP
Deep Learning - MobilenetV2 Hands-On
Inverted Skip Connection, Multiclass Classification
Deep Learning - Tools
wandb, tqdm
Deep Learning - Knowledge Distillation
Knowledge Distillation
Deep Learning - Model Deployment
Model Deployment
Deep Learning - Inferencing
Autograd Profiler
Deep Learning - Strategies Part 1 Before Model Training
Error Metrics, Data Preparation Principles, Transfer Learning, Multi-Task Learning
Deep Learning - Strategies Part 2 Training And Tuning
Bias And Variance, And Things To Try For Performance Improvement From My Experience
Deep Learning - Speedup Tricks
Op Determinisim, Torch Optimizer Tricks, Mixed Precision Training
Deep Learning - Mixed Floating Point Training
FP16, BF16, Mixed Precision Training
Deep Learning - Data Augmentations
Albumentations
Deep Learning - PyTorch Data Loading
RESNET-50 Data Loading, Data Transforms, Custom Data Loading
Deep Learning - Positional Encoding
Transformer Accessory
Deep Learning - Transformers
TODO
Deep Learning - Neural Machine Translation
Hands-On Attention Project
Deep Learning - Speech Recognition
Audio Signal Processing, Spectogram
Deep Learning - Speech Recognition Hands On
GRU-Based Trigger Word Detection
Deep Learning - Attention Mechanism
Bahdanau Attention, Query-Key-Value
Deep Learning - Multi-Head and Self Attention
Multi-Head Attention, Self Attention, Comparison of Self Attention Against CNN, RNN
Deep Learning - Sequence to Sequence Models
seq2seq, encoder-decoder architecture, beam model, Bleu Score
Deep Learning - Word Emojifier Using Dense and LSTM Layers
Emojifier
Deep Learning - Hands-On Embedding Similarity
Similarity and Debiasing
Deep Learning - Hands-On Dinosour Name Generator Using RNN
Deep Learning - PyTorch Versioning
Deep Learning - Word Embeddings, Word2Vec
Word Representation
Deep Learning - RNN Part 3 LSTM, Bi-Directional RNN, Deep RNN
Deep Learning - RNN Part 2 GRU
Vanishing Gradients of RNN, GRU
Deep Learning - RNN
Sequence Models, RNN Architectures
Deep Learning - PyTorch Model Training
Checkpointing
Deep Learning - Ensemble
Ensemble
Deep Learning - Neural Style Transfer
What Conv Net Is Learning
Deep Learning - Face Recognition
Siamese Network, Deep Face
Deep Learning - Face Recognition Prelude
2D Frontalization, 3D Face Alignment
Deep Learning - Hands-On YOLO V1 Transfer Learning
YOLO V1 Theory & Transfer Learning
Deep Learning - Hands-On UNet Image Segmentation From Scratch
UNet
Deep Learning - Performance Metrics
mean Average Precision (mAP), ROC Curve, F1 Score
Deep Learning - Object Detection Notes Part 2
R-CNN
Deep Learning - Image Segmentation
Encoder-Decoder, Fully-Convolutional Networks (FCN), U-Net
Deep Learning - Object Detection Notes Part 1
Convolution Implementation of Sliding Window, OverFeat
Deep Learning - Hands-On ResNet Transfer Learning For CIFAR-10 Dataset
Data Normalization, Conv Net Training
Deep Learning - Classic CNN Models
LeNet-5, AlexNet, VGG-16, ResNet-50, One-by-One Convolution, Inception Network
Deep Learning - CNN Applications
TensorFlow Keras Sequential and Functional Models
Deep Learning - CNN Basics
Filters, Padding, Convolution and Its Back Propagation, Receptive Field
Deep Learning - PyTorch Basics
Neural Network Model Components, Common Operations
Deep Learning - Start Easy, Things I Learned From Training Small Neural Nets
Basic Torch Network With Some Notes on Syntax
Deep Learning - TensorFlow Basics
Nothing Fancy, Just A Basic TF Network
Deep Learning - Softmax And Cross Entropy Loss
Softmax, Cross Entropy Loss, and MLE
Deep Learning - Hyper Parameter Tuning
It finally comes down to how much compute we have, actually...
Deep Learning - Optimizations Part 2
Batch Normalization (BN), Gradient Clipping
Deep Learning - Optimizations Part 1
Momentum, RMSProp, Adam, Learning Rate Decay, Local Minima
Deep Learning - Exploding And Vanishing Gradients
When in doubt, be courageous, try things out, and see what happens! - James Dellinger
Deep Learning - Overfitting
Bias, Variance, Overfitting, Regularization, Dropout
Deep Learning - Batch Gradient Descent
Batch Gradient Descent, Mini-Batch
Deep Learning - Activation and Loss Functions
Sigmoid, ReLU, Tanh, Mean Squared Error, Mean Absolute Error, Cross Entropy Loss, Hinge Loss, Huber Loss, IoU Loss, Dice Loss, Focal Loss
Deep Learning - Auto Differentiator From Scratch
Auto Diff Is The Dark Magic Of All Dark Magics Of Deep Learning
Deep Learning - Introduction
Why Do We Even Need Deep Neuralnets? Data Partition, ML Ops, Data Normalization
Deep Learning - Gradient Checking
First Step To Debugging A Neural Net
2021
Computer Vision - Pinhole Camera Model
This Blog Shows How A Small Magic Peek Hole Captures The World
Computer Vision - Random Tree
Random Tree
Computer Vision - Image Downsampling
Bicubic, Bilinear, Nearest Neighbor Interpolation, Ringing Effect
Computer Vision - ORB Features And Matching
This Blog Shows The Theory and Implementation From Scratch of ORB Features
Computer Vision - Harris Corner Detector
Do Not Cut Corners on Corner Detector - It Will See It
Computer Vision - Warping
Affine Transformation, Perspective Warping, Non-Linear Warping.
Computer Vision - Non Maximum Suppression
Non Maximum Suppression (NMS), Intersection over Union (IoU), TensorFlow non_max_suppression
Computer Vision - Blurring
Gaussian Blurring (Under Active Updates)
2019
Git - Workflows
Git Test Runners
Python - Numpy and Pandas Operations
A Mumbo Jumbo Of Numpy and Pandas Operations and Examples
Python - Python Packaging System
Packaging
Python - Poetry Packaging System and Pip
Poetry, Pip
Python - How To Write Pytest
Pytest Is The New Black (Compared To Unittest)
Python - Jupyter Notebook Common Magic Commands
Jupyter Notebook Common Magic Commands
Python - Python Iterables
Iterable
Python - Functions
Map-Reduce-Filter, Lambda (Under Active Updates)
Python - Python Misc, os, shutil
Print
2018
Docker - Docker Basics
Motication Behind Docker And Docker's Construct
Linux Miscellaneous Thingies
Window Focus, Screenshots, File Differences
Linux - Udev Rules And Systemd Services
Udev Rules Systemd Services
Linux - SSH and X Window System
X Window System, SSH
2017
Math - Distance Metrics
KL Divergence , Chi-Squared Similarity
Math - Stats Basics Recap
Distributions, Covariance & Correlation
Math - Null Space and Singular Value Decomposition (SVD)
How to find Null Space? How to implement that using Singular Value Decomposition (SVD)?
Math - t-SNE
Math - Interpoloation
Linear, Cubic, Bicubic Splines
Math - Matrix Derivatives
Foundation For Everything in Deep Learning and 3D SLAM
Math - Positive Definiteness and Cholesky Decomposition
A matrix is positive definite, if it always sees the glass as half full. But why does the matrix still go to therapy? To break down its issues with Cholesky decomposition. Just Joking.
Math - Eigen Value, Eigen Vector, and Eigen Value Decomposition
What is Eigen Value Decomposition?
Math - Different Types Of Convolutions
Transpose Convolution (U-Net), Dilated Convolution (DeepLab)
Math - Gram Schmidt Orthogonolization And QR Decomposition
Gram Matrix; Super useful in finding forming an orthogonal vector basis, e.g., Singular Value Decomposition
Math - Various Useful Forms Of Matrix Multiplication
Inner & outer Product, Correlation Matrix, etc.