Answering your latest TensorFlow questions! #AskTensorFlow

Laurence Moroney and Jason Mayes team up to answer your #AskTensorFlow questions on today’s episode. Remember to use #AskTensorFlow to have your questions answered in a future episode!

0:24 - How do we extend Keras APIs, model subclassing and generally improve the ease of use?
1:42 - What about web developers who are new to AI, does the version 2.0 help them get started?
6:06 - Does TensorFlow leverage Metal when running on iOS?
7:20 - What’s the best way high school students can better engage with TensorFlow and it’s different components/submodules for their projects and work?
8:50 - What are TF Records, why are they needed for input?

Resources mentioned in this episode:

[ravivijayk]

thanks for another #AskTensorFlow, you should be doing more of these...maybe once a month

[vittoriomalacchia]

#AskTensorFlow
Hi all, ho can we interpret the histogram plots of TensorBoard? Can we capture information regarding the complexity of our model, say if it's to complex of too low complex?

[abhinavprakash]

#AskTensorFlow Is there any plan for making Tensorflow Lucid compatible with TF 2.0.
It's currently supports only TF 1.x
?

[erfantajalli]

#AskTensorFlow
Google Colab helps running our codes with sharing GPUs. Can we expect to have a shared number of CPUs in the near future?
Thank you in advance.

[keitakeita]

I would like to know if i can do a transfert learning for raspberry pi 3 on google colab

[TOP_ENG]

Sorry, but can we use tensorflow with raspberry pi ? and how can we use it if we can? we are use python language but some words does not work Maybe there are library to difind this words.

Thanks.

[arvind]

My question
Why tensorflow has poor documentation?

[undisclosedmusic]

For the 600th time, when are you bringing a MacOS Metal backend?