Build a deep neural network in 4 mins with TensorFlow in Colab

Google Colaboratory is a free Jupyter notebook environment that requires no setup and runs entirely in the Cloud. In this episode of Coding TensorFlow, Laurence shows us how to code, test, and train neural networks right in your browser, without having to worry about installing any kind of runtime. Watch to quickly see an example of how you can use TensorFlow to build a neural network for breast cancer classification...all this happens within Colab!

[LaurenceMoroney]

For those of you wondering -- the reason why I got 100% of the answers right at the end is because of a bug in the code -- spotted by Bruno Fergani (thanks, Bruno!)

Change the loop to for i in range(len(Y_pred)): instead of what it presently is, and you'll see the correct answers here.

This, to me, is a great example of how we can, with the code surrounding a neural network, either train it poorly, or misinterpret its results.

Typically, if you get close to 100% on *anything* with a NN you should instantly get suspicious. It's usually overfitting (as many of you guessed), but it can often be something else too.

[nafiserfan]

Hi @Laurence,
I can't seem to find the .csv data. Can you please help?

[joguns]

Probably one of the best tutors in this field on the net....simplicity

[cheezedust]

Thank you Laurence for this eye-opening tutorial. while training the model, I changed the batch size to 2 while maintaining the 100 epochs. After running the test set, I got 113 corrects and 1 wrong.

[orjihvy]

Love these short well structured videos. Thanks!

[sibyjoseplathottam]

Thank you for the video and notebook. I added the accuracy metric to the Keras compile method and found that the training accuracy reaches above 99% after 100 epochs. If you train it for a few more epochs it will reach 100%. Considering that the test dataset is considerably smaller it is no surprise that the test accuracy reaches 100%.

[semiconductor]

I assume, y_train and y_test are 0 or 1. The network learns to classify breast cancer by converging towards 0.0 or 1.0, but it may not be able to reach these two values exactly for every sample in the training data. In some cases it may only predict 0.96 instead of 1.0. These numerical differences are still accumulated in the loss output, but don't make a difference in the final classification. Thanks a lot for the great educational videos on this channel.

[Bruno.FERGANI]

You're iterating over values instead of indices in the last cell !
Replace line 4 by "for i in range(len(Y_pred)):" and the result should be more accurate... 😁
Thanks for sharing your knowledge BTW !

[Bruceyoutube-oq]

I can not find the csv files, could anyone tell me where and how to download

[michaeltoomey]

Good high level overview. Looks like the csv files from github are gone. so not able to see it work in my colab.

[YGODueltainer]

you know what Google COlab missing? the ability to edit the file directly from the browser without having to download - edited and reuploaded it ... also better interface and user friendly interaction is a must have. either way Google COlab is a still an amazing app to use

[LakshmikanthAyyadevara]

because we are truncating the sigmoid value in the last layer we are getting 100% accuracy for example if we get out put as 0.51 our error is 0.49 but as we are truncating or rounding of the value we are able to get 100 % accuracy (this all depends on the threshold value we chose)

[rachelnayre]

Can I request for the csv files in order to try and demo the sample codes. Thank you.

[giuliacisotto]

Thank you for the great video. I can't download the pre-processed data, tough.. any help?

[firlejczyk]

Very clear and powerful tutorial. If you want to run this notebook locally on your machine to compare performance do not forget to comment or delete these two lines:
from google.colab import files
file = files.upload()

[hieuvutran]

Thank you very much for your great lesson. Could you please upload the csv file again? I cannot download it in 2021. Thank you in advance.

[newjx]

HI, I can't get the files from the link... is it still working?

[izzulfaris]

Hi, can anyone help me with the csv file? im really new. how to download the csv file?

[gedog]

Can't download the data, any ideas why?

[ogsconnect]

Some of the samples missed in training are, fortunately, not present in the test set.