Google Colab is a goldmine for Machine Learning or Deep Learning Enthusiast.

Source: Deep Learning on Medium


Why Colab??

Setting up the environment is always a painful process for working with deep learning or machine learning. Each time, I tried to work on deep learning, I had to pass through that difficulties and spending several hours before even writing hello world. Recently, I found these amazing services from Google called colab.

Colaboratory is a free Jupyter notebook environment that requires no setup and runs entirely in the cloud. With Colaboratory you can write and execute code, save and share your analyses, and access powerful computing resources, all for free from your browser. You can push your changes to GitHub very easily.

How to start?

  1. Go to
  2. Go to file->new python 3 notebook like below:

3. Rename your project like below:

4. Add your code, here is a sample code I have written

import tensorflow as tf
import numpy as np
from tensorflow import keras
model =keras.Sequential([keras.layers.Dense(units=1, input_shape=[1])]);
model.compile(optimizer="sgd", loss='mean_squared_error')
xs = [1,2,3,4,5,6]
ys = [100,150,200,250,300,350],ys,epochs=10)

5. Press the run button like below:

6. You should see the result like so:

Super easy.

Saving to GitHub:

  1. Create a repository in your GitHub account.
  2. go to file->save a copy in Github

It will see a screen like below:

Select your repo and click OK. You are good to go.

How to share?

Click on the share button top right of your screen and it would generate a link.

Request for Improvement to Google:

  1. Make autosuggestion better please, I feel like I am writing code on a whiteboard. By the way, the whiteboard is great since you will be master on syntax but it is painful for faster development.
  2. Leaving it for future….

You can find the code from here.