TensorFlow Tutorial 8 - Model Subclassing with Keras

In this video we learn how to build much more flexible models using keras subclassing. Previously we've seen how to use Sequential and Functional API and hopefully the example demonstrated in the video shows the power of subclassing. I show how to build a ResNet-like model with skip connections which wouldn't even be possible using the Sequential API.

Watch this video to understand ResNet:

❤️ Support the channel ❤️

Paid Courses I recommend for learning (affiliate links, no extra cost for you):

✨ Free Resources that are great:

💻 My Deep Learning Setup and Recording Setup:

GitHub Repository:

✅ One-Time Donations:

▶️ You Can Connect with me on:

[AladdinPersson]

I was inspired and learned the basics of TensorFlow after I completed the TensorFlow specialization on coursera. Personally I think these videos I created give a similar understanding but if you wanna check it out you can. Below you'll find both affiliate and non-affiliate links, the pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link which helps me create more future videos.

[slouma]

Lucky that I bumped on this video, wish to see more code oriented deep learning material like this one. Great job!

[HeyFaheem]

I Searched a lot fot Subclassing like pytorch in tensorflow..
I Finally Found the Best..

[aymensekhri]

Amazing, i hated tensorflow before but now i really like it. it looks like pytroch in logic

[nikitakrasnytskyi]

Thank you very much for the content! It is better than some articles in the net!

[AliRashidi]

This Tutorial was AWESOME!!!! TNX A TON!!!

[ningquanwang]

Thanks for the great video! I am wondering is the call() method in a class a built-in function to convert a class instance into a function? I know there is a __call__() method, but is the call() method the same with the __call__() method?

[Champignon]

Man, i can't believe you don't have more followers, i love your videos and ill be here untill you reach 3.000.000 subs <3.

[SuilujChannel]

to get a summary when using subclassing you can use the build command and specify the shape in the parameter:

# example:
dtc2vec.build(input_shape=(BATCH_SIZE, 2))
dtc2vec.summary()

for some reason i still get the output "multiple" for embedding layers but the other layers show the output shape

[beizhou]

I never thought that the MNIST datasets could also be used this way. Haha. Taking it to the next level.

[wolfisraging]

I remember when I first saw tf allowing this class sub classing like pytorch I immediately fell in love it after first usage. Still lovin it, the only complaint I have is when we summarize the model we don't get to see the shapes of intermediate blocks :} that's why sometimes I prefer functional api. Anyways, great video. 🙂

[filippoguerranti]

Thanks for the amazing videos of this playlist!
May I ask you which IDE are you using and what theme is that?

[legacies]

What is the use of call function? Please explain

[codingyearold]

Newbie question:
@Aladdin Persson
why are they called 3 times in a row?
I was guessing
(None, 28, 28, 32)
(None, 28, 28, 64)
(None, 28, 28, 128)
would be called once every Epoch

[anmarali]

Can you please make a video on "custom padding" like adding a single row above the image and a single col. to the left of the image of 28 X 28 X 1 since keras does not give such flexibility, thanks in advance.

[DanielWeikert]

Thanks for the video. Just one question. Normally we always need to specify the input shape/input_dim of the data we throw into the model. Here we did not do it and it still ran. Can you elaborate on that

[eliashossain]

Could you please specify why you have considered channels[1] rather than channels [0] and channels[2] ?

For example,

self.identity_mapping= layers.Conv2D(channels[1], 3, padding='same')

[AshishKumar-ujox]

Thanks a ton for this excellent series of tutorial. I have a question. Can we make execution of some layers in the subclass conditional? For example if i added maxpool layer to subclass, and I didn't want to run it for the last CNNBlock, then how can I do that.

[shaikrasool]

Sir, make videos on question answering in pytorch and seq to seq in keras

[god-son-love]

How to train with mixed inputs and outputs ?