Kai Lichtenberg - Machine Learning Engineer for Industrial Applications
LinkedIn: https://www.linkedin.com/in/kai-lichtenberg/
Gathering data for image classification tasks can be a annoying hurdle. Wouldn’t it be awesome, if you could just define a keyword for each image class to create a classifier? With the google image search engine this is much more easy than you think.
The KeywordImageClassfier is a fun little project that uses the google-images-download python tool and the fast.ai pytorch library to create image classifiers by just using keywords. In the example case we'll add Corn Dogs to the famous Hot-Dog-Or-No-Hot-Dog Classifier. We'll do that by just specifying the classes 'Hot Dog' and 'Corn Dog', automatically download as much pictures as you want per class from google and fine tune the last layers of a ResNet model pretrained on ImageNet.
https://gist.github.com/KaiLicht/5b7692039455ec77c40a4ab8d6fb6f75
fastai, PIL, google_images_download
- How reliable is such a classifier, when you don't check the images?