Live Coding A Machine Learning Model from Scratch (Google I/O'19)
Ғылым және технология
Do you want to build a machine learning model, but not sure where to start? In this session, learn how to start with an empty Colab notebook, code a model using TensorFlow and Keras, train the model live, deploy it to Cloud AI Platform for serving, and use the deployed model to generate predictions from a web app.
Code from this demo: goo.gle/2VS3uKQ
Blog post: goo.gle/2QcLDIs
Qwiklabs: goo.gle/2ITPFU6
Watch more #io19 here:
GCP at Google I/O 2019 Playlist → goo.gle/2ZPLejw
Google I/O 2019 All Sessions Playlist → goo.gle/io19allsessions
Learn more on the I/O Website → google.com/io
Subscribe to the Google Cloud Platform Channel → goo.gle/GCP
Get started at → cloud.google.com/gcp
Speaker(s): Sara Robinson
T81AAF event: Google I/O 2019; re_ty: Publish; product: Cloud - AI and Machine Learning - AI building blocks; fullname: Sara Robinson;
Пікірлер: 60
While it won't make everything clear (due to time constraints and the fight for human attention), this is a really really helpful start to understanding ML! Thanks a lot Sara! This is probably the first really informative beginner's resource I have found on the topic
Very informative video. You explanation of how ML is doing matrix multiplication under the hood was amazing! As were your descriptions of one-hot and bag-of-words encoding. Never heard of SHAP before, looks like something I would find very useful. Thank you!
from model building to deployment in less than an hour! and handling the live demo gotcha gracefully #awesome
@MasterofPlay7
3 жыл бұрын
she cheated with notes at the back xD
Thanks Sara and GCP ! This was an excellent presentation and demo.
Beautifully explained AI from how to create a model, till how to test a models accuracy using shap
Awesome talk , thank you for the introduction to SHAP !!
Thanks for the content ! But I guess Colab is not adapted for long trainings that last several days right ?
Thanks Sara!! It was a very informative session!!
This is inspiring, I have been doing it the hard way.
Awesome video! This is my favorite from I/O 2019 by far!
very interesting and well-structured presentation
Great talk! Thanks Sara.
Nicely done!! Thank you.
thanks for the demo...learned a lot......
Very nice hands on coding. It would be better if you do it on regular basis on different kinds of problems.
Nicely explained!!
Awesome Very useful thanks Sara
Very informative!
Fascinating!
Good talk. Thank you.
Nice elaboration!!
It's great. Thanks
Great insight!
So helpful!
Great, thank you Sara!
I can't wait to use tensor flow
Awesome video!!
Good one!!
amazing!!!
Thank you!
very useful thank you
Why didn’t you use CountVectorizer from sklearn for tokenizing?
This was class
Why don't use binary cross entropy and not categorical crossentropy ?
thanks so much :)
I like Sara. Amazing content errytime!;-)
Thanks
My model just outputs "Wakanda Forever" pls help
where is the colab file she used in the presentation?
Awesome
❤️
nice
Cool
What's that phython noetbook ??
Can anyone help me with why am I getting different results in the 'code snippets' search option? eg. When I write "auth", "authenticate to your cloud account" option doesn't come.
@possibleps
5 жыл бұрын
yes, same is here with me
@sararobinson1472
5 жыл бұрын
I used custom snippets to add ones I wrote. Details on how to do that here: twitter.com/jakevdp/status/1073251040877633536
Colab has updated to Python 3 and importing the TextPreprocessor class doesn't work for me using the line: from preprocess import TextPreprocessor Error reads: Import "preprocess" could not be resolved(reportMissingImports) Anybody know a solution?
😍
so... can i now build a ML model to stabilize this video?
link for the csv
ML ML ML!
Where can I Get the Code?
Ничего не понял, но очень интересно
im gonna make a startup from it hahahahahaha
Robo
.
yes I have a suggestion, if your going to represent google and not even YOU can get a working live demo by the end, don't blame it on something fictional. It's a bad look, if the employees can't figure it out lol how are the rest of us mortals expected to.. Other then that was a nice quick overview, a verywell setup notebook demo page also.