Skip to content

Instantly share code, notes, and snippets.

View joyhuang9473's full-sized avatar

Yu-Kai Huang joyhuang9473

68 followers · 138 following
View GitHub Profile
@joyhuang9473
joyhuang9473 / CUB_googLeNet_ST_train_val.prototxt
Last active February 3, 2017 03:40
Multi-stream architecture. Refine prototxt from https://github.com/daerduoCarey/SpatialTransformerLayer/blob/master/examples/CUB_googLeNet_ST/train_val.prototxt
name: "CUB_GoogleNet_ST"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
@joyhuang9473
joyhuang9473 / How to install OpenCV 3.1 on Ubuntu 14.04 64bits.md
Created October 5, 2016 09:57 — forked from MarcWang/How to install OpenCV 3.1 on Ubuntu 14.04 64bits.md

How to install OpenCV 3.1 on Ubuntu 14.04 64bits

Update latest packages and installed

$ sudo apt-get update
$ sudo apt-get upgrade

apt-get update - 更新最新的套件資訊 apt-get upgrade - 更新套件

@joyhuang9473
joyhuang9473 / butterfly-2.0-arduino-error-output
Created January 22, 2016 03:08
Arduino: 1.6.7 (Mac OS X), Board: "Arduino Pro or Pro Mini, ATmega328 (5V, 16 MHz)"
/Users/user/Downloads/Butterfly2.0_開源資料/程式碼/MultiWii_x4_mpu6050_last_bluetooth/Serial.ino:155:0: warning: "GPS_COND" redefined [enabled by default]
#define GPS_COND && (GPS_SERIAL != CURRENTPORT)
^
/Users/user/Downloads/Butterfly2.0_開源資料/程式碼/MultiWii_x4_mpu6050_last_bluetooth/Serial.ino:150:0: note: this is the location of the previous definition
#define GPS_COND
^
/Users/user/Downloads/Butterfly2.0_開源資料/程式碼/MultiWii_x4_mpu6050_last_bluetooth/Serial.ino: In function 'void setup()':
Serial:694: error: 'SerialOpen' was not declared in this scope
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week7-error-on-plotting-decision-boundary-of-svm-with-rbf-kernel.m
Last active July 24, 2016 10:42
Version: Mac OS 10.10.5, Octave 4.0.0
% Octave console output
error: set: unknown hggroup property Color
error: called from
__contour__ at line 201 column 5
contour at line 74 column 16
visualizeBoundary at line 21 column 2
ex6 at line 109 column 1
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week7-train-linear-svm-for-spam-classification.m
Created November 23, 2015 15:14
Train Linear SVM for Spam Classification (in spamTrain.mat, spamTest.mat)
% Octave console output
Training Linear SVM (Spam Classification)
(this may take 1 to 2 minutes) ...
Training ......................................................................
...............................................................................
...............................................................................
..... Done!
Training Accuracy: 99.850000
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week7-extracting-features-from-emails.m
Created November 23, 2015 15:08
Extracte Features from Emails (in emailSample1.txt)
% Octave console output
Extracting features from sample email (emailSample1.txt)
==== Processed Email ====
anyon know how much it cost to host a web portal well it depend on how mani
visitor you re expect thi can be anywher from less than number buck a month
to a coupl of dollarnumb you should checkout httpaddr or perhap amazon ecnumb
if your run someth big to unsubscrib yourself from thi mail list send an
email to emailaddr
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week7-preprocess-sample-email.m
Created November 23, 2015 15:02
Preprocess sample email (in emailSample1.txt, vocab.txt)
% Octave console output
Preprocessing sample email (emailSample1.txt)
==== Processed Email ====
anyon know how much it cost to host a web portal well it depend on how mani
visitor you re expect thi can be anywher from less than number buck a month
to a coupl of dollarnumb you should checkout httpaddr or perhap amazon ecnumb
if your run someth big to unsubscrib yourself from thi mail list send an
email to emailaddr
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week7-try-different-svm-parameters.m
Last active November 23, 2015 14:51
Automatically choose optimal C and sigma based on a cross-validation set.
% Octave console output
% C list: [0.01 0.03 0.1 0.3 1 3 10 30]
% sigma list: [0.01 0.03 0.1 0.3 1 3 10 30]
Training ......... Done!
C: 0.010000
sigma: 0.010000
error = 0.56500
====================
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week6-test-various-values-of-lambda-and-compute-error.m
Created November 17, 2015 07:22
Test various values of lambda and compute error
Iteration 200 | Cost: 1.812655e-01
Iteration 200 | Cost: 1.902681e-01
Iteration 200 | Cost: 2.527827e-01
Iteration 200 | Cost: 3.850725e-01
Iteration 200 | Cost: 6.692749e-01
Iteration 186 | Cost: 1.443470e+00
Iteration 111 | Cost: 3.101591e+00
Iteration 61 | Cost: 7.268148e+00
Iteration 33 | Cost: 1.586769e+01
Iteration 20 | Cost: 3.337220e+01
@joyhuang9473
joyhuang9473 / coursera-stanford-machine-learning-class-week6-compute-train-polynomial-regression-and-compute-error.m
Last active November 17, 2015 06:48
Train polynomial regression and comput train error (m = 1 to 12) and cross validation error.
% Octave console output
Iteration 14 | Cost: 1.232595e-32
Iteration 25 | Cost: 4.108651e-32
Iteration 11 | Cost: 3.910038e-28
Iteration 200 | Cost: 5.989594e-08
Iteration 200 | Cost: 8.797460e-04
warning: division by zero.107198e+01
Iteration 200 | Cost: 4.639732e-02
Iteration 200 | Cost: 6.939729e-02
warning: division by zero.922449e+01