TensorFlow Tutorial 7 - More in Depth Example on Functional API

In this video we explore a more real example of using the Functional API to classify multi digit MNIST. So far all we the examples have been simple use cases where you actually can use the Sequential API and it would work, but here we see a real limitation and where we would have to use the Functional API. In the next video we will see how to build even more flexible models using Subclassing.

Code:

Dataset:

❤️ 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.

[baladityaswaika]

Hey! I absolutely love this series. It has taught me a lot about ML programming in a very short time. I also like how you have given resources to theory lectures that help people understand the basic principles involved alongside the advanced math. I'd love to see more such videos, and a suggestion on those lines could be deploying ML models for various platforms, majorly the web and IOT devices. Kudos to you for the amount of sheer effort that has gone into making these videos, and I hope you deliver more such videos in the future. <3
I am a recent CS undergrad with a keen interest in ML and AI, and I always kinda used to mess up how the models work programmatically. After this series, I am sure, I am never making the same mistakes I used to make earlier. Thanks a ton, dude, and I hope we might be able to work on something, together, someday in the future, so that I get to learn from you first-hand.
Anyway, the error actually was caused by the fact that in the code where you have fetched the dataset in and processed it to make it ready for training, you have used a dictionary for the labels, whereby the first number is identified by the key "first_num" of the dictionary for each of the labels, and likewise for the "second_num".
Also, all the best for your future endeavours, and hope you're safe.

[pingng]

Great video!

Regarding the peculiar error, maybe it`s caused by the label keys at line 33 (shown at ~1:55 in video).

[wolfisraging]

By far the tensorflow tutorials.... keep it up

[saiyudhmannan]

in labels you used first_num i guess for the read_image() function. thats why its taking first_num for the labels

[ramsahebprasad]

11:20
in dataset column name is first_num, second_num

[orjihvy]

where can I find the csv files? it doesn't seem to be in the GitHub.

[ramezanifard]

hi. It seems the names you selected for output1 and output2 must be exactly the same names used in the csv file, otherwise you get an error message.

[thiyagutenysen]

I couldn't get the data from the given link in the description. It says You are not authorized to perform this action

[sriharisridhar]

What if both the outputs just read the first number from the training images?

[parthasarathyk]

What if we have multiple objects in one object? Is it same approach or different?

[alis]

The most important part is all about the data management and structure... having two sets of out puts... how do you train test split ... Basically, you just copy pasted some basic code... without going to in to debth as into how the data is going to be managed. Thanks for the video, but would be only interesting for people who dont really understand neural networks but do it to be cool

[somayehseifi]

I have a question, i want to save trained parameters after each batch. how can i do this

[diogosantos]

Hey, many thanks for the tutorials. They are awsome. In case you want to build a hierarchical classifier, where output 1 could help predict output 2 or output 2 depends on result of output 1, what would you change here? The last dense layer? Ex: Dense(10, name=second_num)(output1), does this make sense? Many thanks

[wolfisraging]

That was such a lol error, this is the reason sometimes I gotta struggle with tf, like sometimes the error wouldn't be explanatory at all....

[Andreas]

When I follow the link that leads to the code I get: 404 - page not found
The master branch of Machine Learning Collection
does not contain the path

[danukhan]

error occur beacuse we are giving labels as array of dict and those dict keys are first_num and second_num so for output to go in that branch we need to have that name in that dense layers output

[soheildolatabadi]

Hi, thank you for your great tutorials. one question. how you remove methods and attribute with a shortcut key? for example you remove GRU from layers.GRU at once. thanks

[songhitamisra]

I am getting this wrror:
AttributeError: module 'keras.api._v2.keras.layers' has no attribute 'conv2D'
what can be the reason?

[prashb]

error is because in read_img() in label dict we used first_num and second_num