Version FINAL

Workshop: First steps with Deep Learning


an introduction into deep learning by training a CNN model to classify cats and dogs images.

Introduction



Deep learning has been on a hype peak for the last 2-5 years, and it seems to be here to stay. As a developer, you might be interested in getting in touch with deep learning to see what’s the hype all about, and if you’re not, you should! Deep learning could be a new way of looking at problems and developing innovative ways of solving them.



The goal of the workshop is to give participants first experience in training and using a CNN to classify images. For this purpose, we will be using the most prominent frameworks (Keras & Tensorflow) and take a glimpse of the most popular machine learning community (Kaggle). The workshop is planned to be in Python, which is a popular programming language for deep learning. Nevertheless, you don't need to have Python knowledge to participate!

Development


Participants will go through the process of setting up and coding a simple app to train a CNN on the task of classifying cats vs dogs. while training, the training/validation metrics will be observed.



After the training is completed and the metrics are observed, participants will set up and code an "inference engine" that uses these trained models to classify new cat and dog images.

Requirements


Participants should bring their own laptops and prepare them with as many of the following steps as possible:



  • Install Python3.6.

  • use pip to install Tensorflow, Keras, and Kaggle (optional) for Python 3.6.

  • We will provide a USB drive with the sample data, but if you are interested you can download it before already at Kaggle (you need to have a Kaggle account for that).

Organisation and support



Haitham, Michael, and Jan will be organising and guiding the workshop. They will gladly help you get a better understanding of deep learning and assist you when needed.

Info

Day: 2019-08-11
Start time: 16:45
Duration: 02:00
Room: C115
Track: Development
Language: en

Links:

Files

Feedback

Click here to let us know how you liked this event.

Concurrent Events