Using Tensorflow and Support Vector Machine to Create an Image Classifications Engine

pixabay ai tensorflow post

In this post, we are documenting how we used Google’s TensorFlow to build this image recognition engine. We’ve used Inception to process the images and then train an SVM classifier to recognise the object. Our aim is to build a system that helps a user with a zip puller to find a matching puller in the database. This piece will also cover how the Inception network sees the input images and assess how well the extracted features can be classified.
Continue reading “Using Tensorflow and Support Vector Machine to Create an Image Classifications Engine”

SQLAlchemy in batches: Generating a top playlist

SQLAlchemy is arguably the most powerful and ubiquitous ORM framework for Python.

At Oursky, we have been using SQLAlchemy for quite a period of time and appreciated the flexibility and elegance it provides over the Data Mapper abstraction. No doubt, it works very well for modern web applications but what about long-running background jobs? Would the abstraction get in your ways? (tl;dr: yes, but we still prefer it)

Here are some hands-on experiences from us.

We built a popular iOS application with a song recommendation system at the backend. The system suggests a top list for 20 popular songs.

Previously our editors hand-picked popular songs by download count and gather a new playlist as a recommendation to users. Now, we want to automate this process and generate the playlist weekly.

Continue reading “SQLAlchemy in batches: Generating a top playlist”