Data Science Workshop

We meet to learn more about data science and machine learning by exploring Kaggle competitions.

Kaggle (https://www.kaggle.com) is a platform for predictive modelling and analytics competitions in which statisticians and data miners compete to produce the best models for predicting and describing the datasets uploaded by companies and users.

This time we will discuss Image Classification with TensorFlow and Convolutional Neural Networks.

We will be solving an image classification problem, with a goal to tell which class the input image belongs to. We will achieve this by training an artificial neural network on a few thousand images and make the neural network to predict which class the image belongs to.

The datasets and Jupyter notebook with all the code will be provided during the meetup.

What is required:
Laptop (and charger) with Anaconda installed

You can download Anaconda here:
https://www.anaconda.com/download/

Please also install the following packages:
opencv-python
tqdm
tensorflow
tflearn

Also, please download the data using the link below (it is around 800 MB):
http://files.fast.ai/data/dogscats.zip

OR if you have a kaggle account, you could download it from the competition page:
https://www.kaggle.com/c/dogs-vs-cats/data

Use the link below as a reference for installing new packages in Anaconda:
https://conda.io/docs/user-guide/tasks/manage-pkgs.html

References

Convolutional Neural Networks
https://www.youtube.com/watch?v=FmpDIaiMIeA&feature=youtu.be
https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/

TensorFlow
https://www.datacamp.com/community/tutorials/tensorflow-tutorial