Changsheng

Changsheng

Postdoc in Mathematics from Guangzhou University

Posts by Tags

3D effects

CP936

Unzip file with name in Chinese

less than 1 minute read

unzip -O CP936 <my_zip_file>.zip this piece of code could unzip files with Chinese names, and do not output a mess!

Chinese

Unzip file with name in Chinese

less than 1 minute read

unzip -O CP936 <my_zip_file>.zip this piece of code could unzip files with Chinese names, and do not output a mess!

Driver and CUDA

Explainability

Explanations in Neural Networks

less than 1 minute read

Interpretability (of a DNN) is the ability to provide explanations in understandable terms to a human. F Doshi-Velez & B Kim, 2017。

If Not True Then False

Interpretability

Explanations in Neural Networks

less than 1 minute read

Interpretability (of a DNN) is the ability to provide explanations in understandable terms to a human. F Doshi-Velez & B Kim, 2017。

Nvidia Optimus

Stuck

Transparency

algebra

Notes

2 minute read

Known persons in statistics learning

  • Judea Pearl, Bayesian networks, and causality
  • Geoffrey Hinton, backpropagation, deep belief networks
  • Michael Jordan, popularize probability graphical models
  • Yann Lecun, convolutional neural networks
  • Yoshua Bengio, neural machine translation

basics

basis

basis for convex optimization

1 minute read

Notable Concepts

  • line / (closed) line segments: \theta * x1 + (1 - \theta) * x2, theta in R / in [0, 1]
  • affine set / convex set: \theta * x1 + (1 - \theta) * x2, theta in R / in [0, 1]
  • cone: theta * x, theta in R+ (nonnegative real values)
  • hyperplane / halfspace: a^T x = b or a^T (x - x0) = 0 / a^T x < b, a^T x > b or a^T (x - x0) < 0, a^T (x - x0) > 0
  • balls / ellipsoids: (x - xc)^T P (x - xc) <= r^2 , P = I or other kinds of positive definite solution.
  • polyhedron: the solution set of a finite number of linear equalities and inequalities
  • simplex: conv hull of k+1 affinely independent points, and its affine dimensionality is k. such as line segment, triangle (with interior), tetrahedron (with interior). As well as, unit simplex (x >= 0, 1^T * x <= 1), or probability simplex (x >= 0, 1^T * x = 1)
  • partial order, minimum (最小, for each s in S, s <= s0, or, S included in s0+K), minimal (极小, if s in S s.t. s<= s0, then s = s0, or, Intersection(so-K, S) = {x} )
  • supporting hyperplane

buffer

cache

category1

Future Blog Post

less than 1 minute read

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

category2

Future Blog Post

less than 1 minute read

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

causality

classification

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

clipboard

command

Useful Shell Commands

less than 1 minute read

Count number of fiels in a dir

  • ls | wc -l, all regular files/folders just in this dir
  • ls -a | grep ^\\. | wc -l, all hidden files/folders just in thid dir
  • tree -L 1, list tree just in this dir, and count number of files and folders respectively
  • find ./ -maxdepth 1 -type f,d | wc -l, but will match current dir and hidden files/folders

compress

PDF compressing and splitting

less than 1 minute read

Uploading files might encount size limitation, in which case files need to be compressed and/or split. Here is an effective and easy way in Fedora.

computer

computer vision

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

convex optimization

basis for convex optimization

1 minute read

Notable Concepts

  • line / (closed) line segments: \theta * x1 + (1 - \theta) * x2, theta in R / in [0, 1]
  • affine set / convex set: \theta * x1 + (1 - \theta) * x2, theta in R / in [0, 1]
  • cone: theta * x, theta in R+ (nonnegative real values)
  • hyperplane / halfspace: a^T x = b or a^T (x - x0) = 0 / a^T x < b, a^T x > b or a^T (x - x0) < 0, a^T (x - x0) > 0
  • balls / ellipsoids: (x - xc)^T P (x - xc) <= r^2 , P = I or other kinds of positive definite solution.
  • polyhedron: the solution set of a finite number of linear equalities and inequalities
  • simplex: conv hull of k+1 affinely independent points, and its affine dimensionality is k. such as line segment, triangle (with interior), tetrahedron (with interior). As well as, unit simplex (x >= 0, 1^T * x <= 1), or probability simplex (x >= 0, 1^T * x = 1)
  • partial order, minimum (最小, for each s in S, s <= s0, or, S included in s0+K), minimal (极小, if s in S s.t. s<= s0, then s = s0, or, Intersection(so-K, S) = {x} )
  • supporting hyperplane

cool posts

Future Blog Post

less than 1 minute read

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

detection

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

fedora

gimp

GIMP

less than 1 minute read

GIMP, notable software for image processing in linux

instance segmentation

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

latin abbreviation

Notes

2 minute read

Known persons in statistics learning

  • Judea Pearl, Bayesian networks, and causality
  • Geoffrey Hinton, backpropagation, deep belief networks
  • Michael Jordan, popularize probability graphical models
  • Yann Lecun, convolutional neural networks
  • Yoshua Bengio, neural machine translation

libreoffice

linux

Useful Shell Commands

less than 1 minute read

Count number of fiels in a dir

  • ls | wc -l, all regular files/folders just in this dir
  • ls -a | grep ^\\. | wc -l, all hidden files/folders just in thid dir
  • tree -L 1, list tree just in this dir, and count number of files and folders respectively
  • find ./ -maxdepth 1 -type f,d | wc -l, but will match current dir and hidden files/folders

localization

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

measure

Notes

2 minute read

Known persons in statistics learning

  • Judea Pearl, Bayesian networks, and causality
  • Geoffrey Hinton, backpropagation, deep belief networks
  • Michael Jordan, popularize probability graphical models
  • Yann Lecun, convolutional neural networks
  • Yoshua Bengio, neural machine translation

panoptic segmentation

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

pdf

PDF compressing and splitting

less than 1 minute read

Uploading files might encount size limitation, in which case files need to be compressed and/or split. Here is an effective and easy way in Fedora.

person

Notes

2 minute read

Known persons in statistics learning

  • Judea Pearl, Bayesian networks, and causality
  • Geoffrey Hinton, backpropagation, deep belief networks
  • Michael Jordan, popularize probability graphical models
  • Yann Lecun, convolutional neural networks
  • Yoshua Bengio, neural machine translation

preliminary

recognition

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

semantic segmentation

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

shell

Useful Shell Commands

less than 1 minute read

Count number of fiels in a dir

  • ls | wc -l, all regular files/folders just in this dir
  • ls -a | grep ^\\. | wc -l, all hidden files/folders just in thid dir
  • tree -L 1, list tree just in this dir, and count number of files and folders respectively
  • find ./ -maxdepth 1 -type f,d | wc -l, but will match current dir and hidden files/folders

shortcuts

signature

GIMP

less than 1 minute read

GIMP, notable software for image processing in linux

spacevim

split

PDF compressing and splitting

less than 1 minute read

Uploading files might encount size limitation, in which case files need to be compressed and/or split. Here is an effective and easy way in Fedora.

statistics

Notes

2 minute read

Known persons in statistics learning

  • Judea Pearl, Bayesian networks, and causality
  • Geoffrey Hinton, backpropagation, deep belief networks
  • Michael Jordan, popularize probability graphical models
  • Yann Lecun, convolutional neural networks
  • Yoshua Bengio, neural machine translation

terminal

Useful Shell Commands

less than 1 minute read

Count number of fiels in a dir

  • ls | wc -l, all regular files/folders just in this dir
  • ls -a | grep ^\\. | wc -l, all hidden files/folders just in thid dir
  • tree -L 1, list tree just in this dir, and count number of files and folders respectively
  • find ./ -maxdepth 1 -type f,d | wc -l, but will match current dir and hidden files/folders

tmux

tracking

Common CV Tasks

less than 1 minute read

Common tasks in computer vision:

  • recognition
  • classification, image class labels
  • localization, per-object bounding box labels
  • detection, per-object class+bounding box labels
  • tracking
  • semantic segmentation, per-pixel class labels (all pixels, but do not distinct objects with the same class label)
  • instance segmentation, per-object mask and class labels (only objects)
  • panoptic segmentation, per-pixel class+instance labels (objects and background things)

unicode

Unzip file with name in Chinese

less than 1 minute read

unzip -O CP936 <my_zip_file>.zip this piece of code could unzip files with Chinese names, and do not output a mess!

unzip

Unzip file with name in Chinese

less than 1 minute read

unzip -O CP936 <my_zip_file>.zip this piece of code could unzip files with Chinese names, and do not output a mess!

vim