Archives for xhwang' blog

Reinforement learning 4 - Policy-based

Reinforement learning 3 - Deep Q-learning

Reinforement learning 2 - Value-based

Reinforement learning 1 - Introduction

Large language model system

Deep Learning System

LLaVA

Sparse4D

King of Data

BEVFormer

PETR

Masked autoencoders are scalable vision learners

Detr3D

Clip

Lift, Splat, Shoot

Weighted box fusion

Detection Framework

Autonomous driving system

Attention is all you need

Batch Normalization

Math library

Deep learing milestone

Server benchmark

Unsupervised learing with DCGAN

Generative adversarial network

Deep learning in lua torch

Regularization part II

Regularization part I

Deep visual semantic alignments for generating image descriptions

Tech interview cheetsheet

Deep residual learning for image recognition

Python decorator

Brower spider

An introduction to scrapy

NNDL Chap 1

NNDL Chap 2

A basic introduction of JNI

Pdf to Svg using Poppler and Cairo

Encoding

A neural approach to blind motion deblurring

Learning to deblur

Fully convolutional networks for semantic segmentation

Faster R-CNN

Yolos

Unsupervised learning

Caffe reading - crop layer

Caffe reading - convolutional layer

Caffe reading - loss layer

Derivative of function

Gradient of function

PnP

Structure from motion

Face morphing

Planar Homography

Linux GPU driver

Linux network

GDB usage

Linux command

Linux Graphic and VNC

Linux file permissions and ownership

Linux kernel and OS

Vim usage

Git basic

Docker principle

Docker cheetsheet

Markmap combines markdown and mindmap

Welcome All