Make Pets Found (using AI) - Day 7

3 minute read

Day 7

Well as they say, all good things must come to an end. After a jam-packed week full of hard work, learning, and laughter (and muchas, muchas cervezas), we spent our last morning at El Molino Del Conde wrapping up our hackathon project, before packing our bags and consuming as much remaining food from the fridge as possible.

Image segmentation model in action

Jesús and Sam worked on getting an image segmentation model running and deployed on AWS SageMaker so that we can closely crop pictures of pets, and subsequently run the cropped image through Google Cloud Vision to detect dominant colours of a pet (as opposed to the whole image, including the background). We’d compare the returned colour with our database of colour classification, so we get "ginger", "tabby", "mink" etc.

Following last night’s end-of-week demo, James made some tweaks/fixes to the frontend app.

Malaga airport

After some last minute Rocket League, we bade farewell to the farm cats and jumped in our cars for the airport. Once through security — and determined to keep the party toget- going — George searched every corner of Malaga airport for a pub, then managed to lose his passport somewhere between passport control and the gate. Was this the Alhambra? Who knows. Anyway, after a brief panic to #MakePassportFound, we were all aboard, jetting off into the night.

Gracias España, nos vemos pronto.

Farm cat asleep on chair

View previous (Day 6)

If you’d like to learn more about how Gravitywell can help you benefit from a hackathon, then please get in touch.