Ein Vortrag von penguinmeanc3 auf der GPN17.
The talk will introduce a split into model, loss, dataset and estimator that keeps your code clean and easy to understand. For each of those 4 topics details how to implement it in an efficient, reusable way are explained.
The talk will assume basic knowledge about deep learning, since it will focus on implementation and no theory.
You will learn:
- Writing good quality deep learning code
- Implementing a model from scratch
- Implementing a loss
- Loading a dataset
- Training a model
You will *not* learn:
- What to use Deep Learning for?
- What is a CNN, GAN, RNN, etc.?
- That latest super weird feature of tensorflow.
One more thing: "The answer to the ultimate question of life, the universe and everything is 42." [The Hitchhiker's Guide to the Galaxy]
Links
Fahrplan |
Hauptseite | Feedback | FAQ
2³² Stars In The Sky Abschlussrunde mit Vorstellung FreifunkBW::Camp Alice explodiert! Begrüßung und Einleitung Bondage-Workshop BorgBackup Treffen Build yourself a SNMP replacement Building a Photobooth Closing und Review Combining the Intertubes using Multipath TCP Critical Mass CyberMorning Show Cybern Demoshow Die manpages.debian.org-Modernisierung Digitalisierte Stromnetze und Smart Meter in Deutschland Einführung Infotresen Einführung in Onshape Einführung in die Chaosvermittlung Electronic GeekBag Esoterische Programmiersprachen FreeBSD: The Power to Serve a Community Freifunk Interconnectivity Freifunk-Admin-Talkrunde From Mirai to Apple Guerilla Stricken Gulasch Karaoke Gulaschausgabe HTTP Security Header Hack the Badge - Preisverleihung Hackertours Haecksenfryhstyck How to fly to the Moon How we bodged the Badge Improving the Web of Trust with GNOME Keysign Introduction to Automated Binary Analysis Jonglier-Workshop Lightning Talks Lossless Data Compression Mammut statt Vogel Mate Making DIY McFly McFly Menstruation Matters Mitgliederverwaltung für Erfas My Little Pony - Videoanalyse ist Magie Network Flow Analysis using Netflow protocols and tflow2 Neues ECAD-Programm horizon OWASP TOP 10 OWASP Top 10 Privacy Risks Project PGP Keysigning Panik überall Pixel-Art Workshop Playing Studio Sets Live with Ableton Podcasten QR-Codes SHA2017 Orga Meet @ GPN17 Salt-Orchestrated Software Defined Freifunk Backbone im Hochstift Smarthome mit ioBroker Sysadmin Nightmares The Elektr0nic Window Towards a more secure operating system without sacrificing usability Vertrauen ist gut, Kontrolle ist besser. Virtual Reality mit Freier Software WCW 2017 Livestream Webserversecurity 101 Werwölfe von Düsterwald What to hack Wie kommt eigentlich das Internet von Hamburg nach Stuttgart? ZFS replication with zrepl ffbw.de Workshop git-dit gokrazy: ein Go userland für Raspberry Pi 3 appliances hacking galaxy S8 iris recognition small modifications and embodied connectivity the dark side of the wifi Æ-DIR Installation Workshop