Deploy your first end-to-end ML model using Streamlit

Deploy your first end-to-end ML model using Streamlit. I am going to deploy a Supervised machine learning model to predict the age of a Abalone and in the next part of the tutorial we will host this web app on Heroku.

Painting sketches with ML

Art is one of the things that separate us from the machines and and from what machines are capable of doing. Algorithms don’t tend to be creative, they try to automatize certain decisions, or replicate some rules created by other humans. This tasks is where the machines excell the humans. That is why I’ve always been intrigued on algorithms that produce art: machines that can produce music or paintings by their own. Take for example Google’s deep dream project, where a team trained a convolutional neural network to detect objects on images, but then they forced that model to find objects where they were not present, resulting on some psycedelich images. Or look to Google’s Magenta project. Magenta Studio is a Google Brain project “exploring the role of machine learning as a tool in the creative process”. Of course we are far from letting the machines produce art, but nowadays there are plenty of softwares to assist artist to guide them on their work. These softwares uses AI to recommend or correct some aspects of their work. Nowadays also is very easy to train a deep learning model to do certain tasks. That is what we are going to do on this post, we are going to train a deep learning model to paint black and white sketches. We are going to use Keras API from TensorFlow 2 to develop and train our deep learning model. You can find all the code on this Github repo.

Integrating AWS SageMaker Models with QuickSight.

Have you ever wondered how can you add ML Predictions to your BI Platform in an easier way and share to client ? Don’t worry! One of the…