Getting Started with TensorFlow 2.0 (Google I/O'19)
Вставка
- Опубліковано 14 чер 2024
- TensorFlow 2.0 is here! Understand new user-friendly APIs for beginners and experts through code examples to help you create different flavors of neural networks (Dense, Convolutional, and Recurrent) and understand when to use the Keras Sequential, Functional, and Subclassing APIs for your projects.
Watch more #io19 here: Machine Learning at Google I/O 2019 Playlist → goo.gle/2URpjol
TensorFlow at Google I/O 2019 Playlist → bit.ly/2GW7ZJM
Google I/O 2019 All Sessions Playlist → goo.gle/io19allsessions
Learn more on the I/O Website → google.com/io
Subscribe to the TensorFlow Channel → bit.ly/TensorFlow1
Get started at → www.tensorflow.org/
Speaker(s): Josh Gordon, Paige Bailey
TCDFE8 event: Google I/O 2019; re_ty: Publish; product: TensorFlow - General; fullname: Josh Gordon; - Наука та технологія
the fact that tensorflow 2.0 includes Keras is enough reason for me to upgrade
Thanks, Josh you explanation crystal clear especially different from beginner and experts.
22:19 Excellent. I like this conversion script that also shows what new 2.0 API calls have been converted from the 1.x API
That flickering!!!
Hmm I thought it was my computer GPU card?
Skynet is here. Hello world, baby.
Thank you very much for this tool and all the videos from Germany!
I'm approaching TensorFlow for my master thesis and wow, it seems amazing!
That glitch though. This was one of the first videos I played on my brand new, super-expensive TV and almost had a heart attack.
Amazing changes guys, amazing!
Always great to see Josh, great talk from both of you! Thank you!
Thanks. This was very useful.
Funtastica! Great presentation.
Josh is such an inspirational personality.
Great one.
23:48 “I'mma let you finish …”
Good job with finally fixing the horrible nightmare TF1 was. Also please add a seperate tutorial for performance optimization. I and engineers that work on production systems would grealty appreciate.
Thank yuo very much
*Josh Missing your Machine learning recipes* ♥️
Have a try
that help lot
24:35... Multiplying matrices in python (numpy) is actually made in C (and Fortran) so using tf is not necessarily faster at all. And certainly not orders of magnitude faster when run on the same CPU.
excellent josh
Swift TensorFlow ❤️
Wow long time no see vid from Josh.. Last time i guess from his ML Recipe series.
where are those codes sources notebooks colab files access?
Great.
Can i get access to these slides? Are they available public?
Does someone have a link to the Coursera and Udacity courses he mentioned at around 6:48?
I'm not sure, but in the News & announcements section of www.tensorflow.org there are links to bit.ly/2EFvFCp and www.udacity.com/tensorflow. Someone must be living in the past at Google, because the posts are dated Mar 6, 2018, but clearly they are from 2019.
Tensorflow is becoming PyTorch
You can remove flickering by drop the resolution to 360p
I'm new to deeplearnig, please suggest which version of TensorFlow should focus? Please any suggestion.
TensorFlow >= 2.0 for sure, far away simpler.
Do you provide the slides?
Finally my nightmares are over. TF
13:12 for students who want to know the details, print the grad
the slides are flickering quite badly :(
lol i thought it was my laptop, restarted my laptop twice!
What model can I use to create a self aware machine?
Oh and is there Tensor flow for rust.
Does Google has a conversion script from PyTorch to tf2.0?
We need a decent golang API!
is tf 2.0 available for gpu ?
Hopefully you already found it. www.tensorflow.org/alpha/guide/using_gpu
What is the minimum number of sentences a NN would need to be exposed to, in a given language, in order to gain a majority understanding of said language? Could this help humans classical understanding of how to learn a new language?
Define "understanding"! 😉 A month ago OpenAI's GPT-2 trained on 40 GB of English text to be able to blather on in the style of opening sentences, answer comprehension questions, write decent summaries, etc. Several years ago many people took a simpler machine learning algorithm and got it to produce text in the style of Shakespeare or whomever using much less data. But is that really understanding the concepts that words and syntax convey?
wow
I wish I could watch through this, but I cannot get past the flickering of the slides. It hurts my head.
The Great
But did it get any easier to use tensorflow in C++ directly ?
That bitly link @ 4:51 doesn't seem work or is it just me??? " bit.ly/mini-nmt "
If you'd like to watch a hands-on workshop after this video, you can check this one out from SciPy Tokyo: ua-cam.com/video/Yyv-ng0_OTU/v-deo.html
Go to experience TF now~
I dont understand a thing.. but i like this..
Slides are here: drive.google.com/file/d/1N0Fq1XtzFzHy3vznq4w2M3sAp8TJrjKt/view
Hi everyone, here are the slides for this talk: bit.ly/2LrsLGO
did the sun wash out the screen
first
None of these work:
bit.ly/tf-linear
, www.tensorflow.org/alpha/uotrials/quickstart/beginner
Make some basic tutorials. Fancy talks don't produce.