We all enjoy waffles or ice cream unless you are lactose-intolerant. This basic web app is able to detect and identify waffles or ice cream in a photo.
YoloV5 was used to train the default model and labelling the images was done using MakeSense. The Waffles or Ice-Cream dataset was used for training and validation.
<script async src="//embedr.flickr.com/assets/client-code.js" charset="utf-8"></script>Few steps to follow before getting started.
- Download the YoloV5 github repository
- Create a directory called
runs
with the following subdirectoriestrain\weights
- Move
best.py
to the newly created directly (this contains the weights of the trained model)
- The model only used 74 images for training and validation. It can be significantly improved for better results
- Training was done using Google Colab using a GPU