Yahoo open-sources a deep learning model for classifying pornographic images

Yahoo today announced its latest open-source release: a model that can figure out if images are specifically pornographic in nature.

The system uses a type of artificial intelligence called deep learning, which involves training artificial neural networks on lots of data (like dirty images) and getting them to make inferences about new data. The model that’s now available on GitHub under a BSD 2-Clause license comes pre-trained, so users only have to fine-tune it if they so choose. The model works with the widely used Caffe open source deep learning framework. The team trained the model using its now open source CaffeOnSpark system.

[aditude-amp id="flyingcarpet" targeting='{"env":"staging","page_type":"article","post_id":2068799,"post_type":"story","post_chan":"none","tags":null,"ai":false,"category":"none","all_categories":"big-data,business,","session":"C"}']

The new model could be interesting to look at for developers maintaining applications like Instagram and Pinterest that are keen to minimize smut. Search engine operators like Google and Microsoft might also want to check out what’s under the hood here.

“To the best of our knowledge, there is no open source model or algorithm for identifying NSFW images,” Yahoo research engineer Jay Mahadeokar and senior director of product management Gerry Pesavento wrote in a blog post.

Baidu, Facebook, Google, Microsoft, and Twitter have also open-sourced different deep learning systems in the past.

But this software shouldn’t be considered perfect.

“We do not provide guarantees of accuracy of output, rather we make this available for developers to explore and enhance as an open source project,” the authors of the open_nsfw project write in a disclaimer.