The content of this post is mostly copied from here. The reason I do this is to ensure that that really helpful post will be accessible and to add few modifications.

1. Update and dependencies

# Update apt-get
sudo apt-get update
sudo apt-get upgrade

# Kernel header
sudo apt-get install linux-headers-$(uname -r)

2. Install NVIDIA CUDA Toolkit

Go to https://developer.nvidia.com/cuda-downloads and download CUDA Toolkit 9.0 (Legacy) for Ubuntu 16.04. Download deb (local) which is 1.2 GB.

sudo dpkg -i cuda-repo-ubuntu1604-9-0-local_9.0.176-1_amd64.deb
sudo apt-key add /var/cuda-repo-9-0-local/7fa2af80.pub
sudo apt-get update
sudo apt-get install cuda-9.0
# Reboot
sudo reboot

vi ~/.bashrc
# add those 2 lines at the end of the file then save it
export PATH=/usr/local/cuda-9.0/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-9.0/lib64:$LD_LIBRARY_PATH

Then, execute the following commands and check that nvidia-smi works.

source ~/.bashrc
sudo ldconfig
nvidia-smi

3. Install cuDNN 7.2.1

Go to https://developer.nvidia.com/cudnn, login/register, go to cuDNN Download, Archived cuDNN releases and download cuDNN v7.2.1 (August 7, 2018), for CUDA 9.0. Now, for some reason, it seems that that version of cuDNN is only available for CUDA 9.2, but we can just change the download links manually from the CUDA 9.2

cuDNN v7.2.1 Runtime Library for Ubuntu16.04 (Deb): https://developer.nvidia.com/compute/machine-learning/cudnn/secure/v7.2.1/prod/9.0_20180806/Ubuntu16_04-x64/libcudnn7_7.2.1.38-1_cuda9.0_amd64
cuDNN v7.2.1 Developer Library for Ubuntu16.04 (Deb): https://developer.nvidia.com/compute/machine-learning/cudnn/secure/v7.2.1/prod/9.0_20180806/Ubuntu16_04-x64/libcudnn7-dev_7.2.1.38-1_cuda9.0_amd64
cuDNN v7.2.1 Code Samples and User Guide for Ubuntu16.04 (Deb): https://developer.nvidia.com/compute/machine-learning/cudnn/secure/v7.2.1/prod/9.0_20180806/Ubuntu16_04-x64/libcudnn7-doc_7.2.1.38-1_cuda9.0_amd64

Install them in the right order:

sudo dpkg -i libcudnn7_7.2.1.38–1+cuda9.0_amd64.deb
sudo dpkg -i libcudnn7-dev_7.2.1.38–1+cuda9.0_amd64.deb
sudo dpkg -i libcudnn7-doc_7.2.1.38–1+cuda9.0_amd64.deb

Verify the installation

cp -r /usr/src/cudnn_samples_v7/ $HOME
cd $HOME/cudnn_samples_v7/mnistCUDNN
make clean && make
./mnistCUDNN

You should expect a “Test passed!”.

CUPTI ships with the CUDA Toolkit, but you also need to append its path to the LD_LIBRARY_PATH environment variable

vi ~/.bashrc
export LD_LIBRARY_PATH=/usr/local/cuda/extras/CUPTI/lib64:$LD_LIBRARY_PATH
source ~/.bashrc

4. Install TF and verify it works

pip install tensorflow-gpu

Run

import tensorflow as tf
with tf.device('/gpu:0'):
a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')
c = tf.matmul(a, b)

with tf.Session() as sess:
print(sess.run(c))

If this script runs without giving any error you are using gpu version.

My computer:
Windows 10, Python 3.4, OpenCV 3.0.0

I had uncountable desperate attempts to install OpenCV 3.0 in my machine, including the always last plan when installing software: building it from the source. There is an apparently nice tutorial from the official OpenCV webpage which didn’t work for me because I needed to do a couple of steps, so please, try to follow this tutorial (section Building OpenCV from source) with this addition tips:

• 7.2: Use the path you want, but remember that you will not be able to delete it (because you need to refer to that path) so choose wisely.
• 7.4: You can use any Visual Studio. In fact, I used Visual Studio 13. Just remember to specify it when configuring CMake
• 8,9,10,11: When you are checking and unchecking all those checkboxes you will realize that many of the options are not listed on the provided pictures. What to do in that case? Easy: just leave it there as it is.
• 16: Some of the projects will not be built and will be skipped. Don’t worry.

Now, it’s supposed to be installed in your computer, and if you try to import cv2, it should work.
However, at least for me, it didn’t work. The final step to get rid of that annoying message is to add the appropiate path to the PATH system variable. This is the path that you have to add: X\bin\Release where X is the folder where you compiled it.

I hope this is helpful. This could have saved me many hours…

Since Machine Learning and, in general, Artificial Intelligence became my favorite subject, I have spent a lot of time learning about it by myself. I consider that a good, readable and pleasant book can be key in learning about such difficult topics. I have to say that I started reading which probably is the most famous book in this issue: Machine Learning and Pattern Recognition (Bishop), but I failed at finishing it. Plenty of maths, abstract concepts and no real examples make this book very tough, in my opinion. I think this book collects and admirable amount of work and may serve as a great reference, but in order to fully comprehend and learn from an undergraduate background, it can be hard.

Because of the lack of examples, I tried to find a book with examples in some programming language, as Machine Learning: An algorithmic Perspective does. However, I didn’t like it very much neither, because it uses Python classes that you cannot see them from inside. A quite understandable argument is that you don’t really need to understand how it compeltely works from inside in order to understand the general idea of some algorithms, but I think that the only way to understand how an algorithm works is by programming it.

I tried to read each chapter of this book carefully and spending a lot of time researching, reading papers, watching Youtube videos to help me to understand concepts and of course writting down some notes. I have decided to publish all the stuff I’m doing, from personal written notes to source code because it may help more people who are reading this book or who simply try to understand specific concepts.

As I don’t want to write a very long post about it, this entry will serve as an index and for each chapter I consider interesting, I will write a post uploading my own stuff and giving some explanations.

Machine Learning: An Algorithmic Perspective
1.-Introduction
2.-Linear discriminants
3.-The Multi-Layer Perceptron
4.-Radial Basis Functions and Splines
5.-Support Vector Machines
6.-Learning with Trees
7.-Decision by Commitee: Ensemble Learning

2.-Linear discriminants

Downloads: perceptron.pdf, activation.m, NN2outputs.m, NNand.m
Contents: Transfer function, Why bias is needed?, Learning rate, examples, Matlab code.

3.-The Multi-Layer Perceptron

Downloads: MLP.pdf, NN231.m
Contents: Backpropagation, Multi-Layer Perceptron
Further study: Create a general algorithm to use a NN with N inputs, M layers, P nodes, Q outputs.

4.-Radial Basis Functions and Splines

Downloads: kmeans.pdf, kmeans.m
Contents: K-Means algorithm
Further study: Go back to this section in a future to better understand it. Study more about splines.

5.-Support Vector Machines

Downloads: SVM.pdf
Contents: SVM algorithm explained, Non-linear SVM, several examples
Further study: Implement this efficiently in Matlab, learn more about Non-linear SVM, learn how to find support vectors among all others automatically

6.-Learning with Trees

Downloads: Trees.pdf
Contents: Example of Decision Tree (classification)
Further study: Learn/implement C5.0 algorithm, and CART (for regression).

7.-Decision by Commitee: Ensemble Learning

Downloads: Adaboost.pdf
Content: Adaboost formulae and 2 examples
Further study: implement Adaboost in Matlab, example of bagging and Mixture of experts

During my epic trip to Poland and Czech Republic with some friends an incident happened. At the half of the trip I realized that there was something wrong with my Kindle screen, but I didn’t know what was going on with it. I was thinking that probably the problem is that’s broken, but I wasn’t sure at all and I tried to restart and reset a couple of times.

When I arrived at home, I tried to find pictures of a broken screen Kindle, and it was definitely that. Now I know how a broken screen looks like.

Broken screen

I bought this Kindle around 4 years ago, and I liked it very much, even more than this non-keyboard version Kindle that we can see nowadays, so I didn’t want to buy a new one which is actually more expensive than repairing my old one. I was afraid because I haven’t opened any device like that before, but there is always a first time for everything, and the time came. By the way, nowadays I think we can buy a new Kindle for less than 100€ and I paid around 250€ for this one (it was expensive because it came from the US and I had to pay very high taxes).

Anyway, I found a screen replacement in eBay and it cost around 30€ and one month to arrive. After open the Kindle I realized I need a very small screwdriver, so I ordered a this kind of screwdriver from the Internet and another month I had to wait!

Replacement. Thanks God the instructions were there.

As I’ve never done this before, I was afraid and I searched a tutorial, and here it is: http://www.youtube.com/watch?v=ObFE8sPoXfw but actually, it’s basically this: remove screws, change screen and put them back. Actually, I can say that the most difficult part was putting on and off the plastic case. It’s very difficult and you have to be very careful.

Different parts of the Kindle.

One particular part where we have to take special care is then removing those things I marked using red color. We have to lift them up and pull back that thing they have inside. It looks like paper.

When I fully disarmed my dear Kindle, I could see that the screen was broken indeed.

Kindle broken screen, how it looks like from inside and outside

I had a very stupid problem I want to write about, so if you ever do this, charge your battery at first! When I did this the first time, it looked like it didn’t work, so I put the broken one again. After this I realized that the battery was empty, so I charged it and did it again, and

Kindle working again, aka orgasm

Introduction
Last week, in the middle of my timetable gap, waiting with my German friend for the Finnish for Exchange Students class he showed me the Apple maps application, and I really liked how you are able to see projected sunlight in Earth, and as I really liked space stuff pictures, I thought it would be nice if I’d have a dynamic wallpaper that changes automatically where I can see this, thus comparing sunlight hours between my home country and Turku (Finland), where I’m living nowadays.

At first, I saw my own skills so limited since I mostly know about PHP, C, Java, and a little bit of other programming languages. After this I made me promise to learn some day Python, but anyway, knowing about C++ would also be okey in this situation. My final decision? Powershell!

Getting down to work
I have never programmed using Powershell, and I was quite surprised how a lot of things can be done in a so easy way.
I researched about this kind of planet and sunlight images, and I found a Czech webpage where I can select coordinates and zoom, so I just adjusted this to my needs and this is the result.

As I have never programmed in PS, I researched how to change and update the wallpaper, and although it was quite easy to implement (only two lines), I decided to rely on the operating system itself (it is always suppose to have higher perfomance, rather than programming oneself the same) and the only work I did in PS is to download a couple of images which will be rotating every 5 minutes (also they are downloaded every 5 minutes).
Note: I selected a 5 minutes interval for mainly two reasons: I am not able to send too many requests to the Czech wesite, I think it’s enough and this way I don’t spend too many resources.

I’m also interested in making some kind of video where I can see the sunlight at the same hour every day, in order to see how the sunlight changes during the year, so I also programmed this in the script below.

Source code

<#
 # This function will save an image given source and destination
 # @param source of the image.
 # @param destination where the image will be saved.
#>
Function SaveImage
{
    #Get the params and cast them into strings
    $source = [string]$args[0]
    $destination = [string]$args[1]
    
    #Download it, and wait for 5min
    $wc.DownloadFile($source, $destination)
    Start-Sleep 300

}


$source = "http://www.fourmilab.ch/cgi-bin/Earth?img=learth&imgsize=1000&opt=-l&lat=50&ns=North&lon=20&ew=East&alt=2000&date=0&dynimg=y";
$wc = New-Object System.Net.WebClient
$date = Get-Date
#Name for my picture I will store in the other folder
$pictureName = "$($date.Day)-$($date.Month)-$($date.Year).jpeg"
#Other folder where I will store all the pictures to make the movie
$pictureFolder = "C:\Users\JuanMiguel\Pictures\light\"
$pictureFullPath = "$pictureFolder$pictureName"
#Where I will store the images I will use as wallpaper
$destination = "C:\Users\JuanMiguel\image"

#I will save the picture always after 19h
while($date.Hour -lt 19)
{
    SaveImage $source "$($destination)1.jpeg"
    SaveImage $source "$($destination)2.jpeg"
    #I take the date again
    $date = Get-Date
}

#Check if that picture exists, otherwise I will save it
if(!(Test-Path $pictureFullPath))
{
    SaveImage $source $pictureFullPath
}

#Endless loop
while(1)
{
    SaveImage $source "$($destination)1.jpeg"
    SaveImage $source "$($destination)2.jpeg"
}

As PowerShell is a high level programming language (very high indeed), I tried to program the script in a non-traditional way, checking the less information as possible. Of course, it would have been cleaner if I’d only used one infinite loop asking all the time about the hour and checking if the image I want to save exists, but that way I have to ask many times to the computer, therefore, more work, more wasted resources, less battery, etc. Sometimes it’s better to think more about the performance and less about how easy to read the code is, mainly when we have so simple code like this.

17h and almost dark.. but winter will be fun!