Aktionen

AI on Rasp Pi

Aus exmediawiki

Version vom 31. Mai 2020, 15:03 Uhr von C.heck (Diskussion | Beiträge)
(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)

Seminar, 28.11.2019

Präsentationsfolie:

Keras-image.png



Camilo Sandoval präsentiert heute:

»Stochastics Walks on the Latent Space - Cloud Representation and Text Extrapolation of Semantics Deduced from Nietzsche's Writings«
 ... & how to setup a raspberry pie to run & expand it by yourself? ^_*)

June 27, 2016

The US Air Force has just completed dogfighting trials in a simulator, pitching the software against retired Air Force Colonel Gene Lee. The AI – which ran on a $35 RaspberryPi computer – was deliberately handicapped but still managed to shoot down its fleshy opponent every time and evade his attempts to kill it.

ALPHA is "the most aggressive, responsive, dynamic and credible AI I've seen to date," Lee said. "I was surprised at how aware and reactive it was. It seemed to be aware of my intentions and reacting instantly to my changes in flight and my missile deployment. It knew how to defeat the shot I was taking. It moved instantly between defensive and offensive actions as needed."

install Processing on a Rasp

type in terminal:

curl https://processing.org/download/install-arm.sh | sudo sh


...or go to Processing’s downloads page to download and install it on your own.

Processing2.png

RemoteDesktop mit Teamviewer

Mit der Software Teamviewer können wir aus der Ferne auf unsere Lab-Rechner zugreifen.

Eine Anleitung findet ihr hier: Per_Teamviewer_auf_AI-Lab-Rechner_zugreifen



KI-Workaround installieren on Raspberry Pi 4

type in Terminal:

notwendigen Abhängikeiten installieren:

 sudo apt-get install -y libatlas-base-dev libblas-dev liblapack-dev libhdf5-dev libc-ares-dev libeigen3-dev build-essential libsdl-ttf2.0-0 python-pygame python3-venv festival virtualenv Pillow numpy pygame

Ordner jupyter-sandbox erstellen

mkdir jupyter-sandbox

in Ordner navigieren

cd jupyter-sandbox

Virtual environement venv erstellen

python3 -m venv venv

'venv aktivieren

. venv/bin/activate

pip installieren

sudo apt-get install -y python3-pip

upgrade

pip3 install --upgrade setuptools

passende Version downloaden unter: https://www.tensorflow.org/lite/guide/python und in meinen derzeitigen ordner kopieren:

cp ~/Downloads/tflite_runtime-1.14.0-cp37-cp37m-linux_armv7l.whl .

oder direkt in den jeweiligen Ordner mit wget downloaden:

wget https://dl.google.com/coral/python/tflite_runtime-1.14.0-cp37-cp37m-linux_armv7l.whl

Tensorflow_Lite installieren

pip3 install tflite_runtime-1.14.0-cp37-cp37m-linux_armv7l.whl 

jupyter notebook installieren

pip3 install jupyter

tensorflow installieren

pip3 install tensorflow

keras installieren

pip3 install keras

Virtual environment upgraden

sudo pip install --upgrade virtualenv

jupyter-notebook starten

jupyter-notebook

notwendige Files für heute

Der Ordner in der KHM-Wolke mit den notwendigen Files liegt unter: https://wolke.khm.de/index.php/s/BqjYn2GnTjdJjX9


Mit Text visuell arbeiten...(konkrete Poesie)

GNU/Linux 4 artists