Deep learning with Python - Chapter 7 - 7.2 - Keras sequential vs functional API

[@PhD.YouTuber]

You are doing amazing explanation with the clear understanding and knowledge you have. Thanks

[@Easy_Eds]

Your explanations are clear and easy to understand. You explain the details left out of other videos.

[@coemgeincraobhach236]

I literally just started using the functional API instead of sequential and was confused why there was two ways of building models, so handy this came up as recommended. Functional makes way more sense in the long run. Thanks!

[@joapen]

very didactic way to explain how it works, awesome video, many thanks!!!

[@lfmtube]

Great density and better info quality. Congratulations and Thank you. I am a new subscriber

[@NuclearSpinach]

Great explanation. Functional API actually makes more intuitive and clear sense to me

[@monamijaiswal5868]

Great explanation sir, I'd be very helpful if you create a playlist for neural network videos which are already on your channel

[@elielberra2867]

Thank you! This video was very clear!! and the handwriting is impecable haha :)

[@habibkettana4887]

Thanks a lot M. Badri, it was very well explained.

[@eduardo.garcia]

Finally I understood this!!! Thanks a lot

[@NatashaShrivastava-xz1rm]

Excellent video

[@COOKINGBIRD]

Thank you so much for this information.Would you be so kind to so how to do RBFN training , validation in Keras

[@abdullahiabdi5887]

Thank you very much sir. This is a great explanation! and this came very handy for my research.

[@husseinfg1478]

Very useful channel.

[@mohammedabdo.m576]

This is ANN or RNN model ?

[@mozheet7758]

Can we use the second method for multiple outputs?

[@mahendrank9879]

yep

[@mehdisoleymani6012]

Thanks a lot for your great courses, is it possible for you to explain my question? How should we add non-image features to our CNN model (features like cat and dog prices) to our flatten layer? Does the CNN model new added features belong to which input image?

[@utkarshsingh2675]

Important video

[@pragyan11114]

How to know howmany neurons should be there when you add dense .for each layers??

[@rs9130]

hello author, i want to train a model to predict heatmap (mean square error loss) and binary segmentation (binary cross entropy loss). i tried to train model using multi branch (2 branch duplicates for 2 output). but the the final output will favour for only one type of output. For example when i train using model.fit with equal loss weights, the output is good for heatmap, but binary mask output is wrong and gives pixels 1 for the regions similar to heatmaps. And when i train using gradtape loop, the output is good for segmentation mask, but heatmaps are wrong and looks like masks. how can i solve this, please give me your suggestion. thank you

[@husseinfg1478]

great explanation.

[@juanete69]

Hello. Why do you write input_shape=(8, ) and not input_shape=(8) without the comma.

[@HS0]

Can't write " input_shape=(8) " , We can write input_shape=(8,) to tell python : " The input dimension = 1 , and the row = 8 , but we don't have columns Because we are in first dimension "

[@temp20111]

Great thank you

[@rachidelfermi6759]

thanks this explaint it clearly

[@abhinavkant]

Thanks

[@egehanasal710]

THANK YOU SIR

[@Rsudano]

Thank you :)

[@gauravbhasin2625]

you did not explain the basic architectural difference....

[@ayushgupta1881]

Thanks a lot !

[@ThePantafernando]

Is it just me that think those API really full of bad smells? For starters, why would someone write two ways to do the same thing? Thats making stuffs more complicated for no real gain in the send. That way of chaining functions in functional programming really hurt my ways when compared to classical chaining from functional programming.