AI App Predicts the Popularity of Social Media Posts

Cornea AI takes the guesswork out of photo sharing by using deep learning to predict how well your photo will do on social platforms.

Users can either take a photo, or import one from their gallery and the AI will score the photo — it then suggests popular filters and hashtags to increase the popularity of the photo once it’s shared on Facebook or Instagram.

On the back-end, the app developers are using GeForce GTX 1080 Ti GPUs with the cuDNN-accelerated Keras and Lasagne deep learning frameworks to train their five different neural networks: (1) for style transfer which transfers the style of any artist or image to a photo; (2) for transferring color which segments the image to transfer colors; (3) for hashtagging popular images – once an image is uploaded, the network looks for similar popular images and recommends the hashtags they use; (4) recommending hashtags by analyzing what’s in the user’s photo to help make the image trend; and (5) popularity predictor network that is trained to differentiate between popular and non-popular images and give similar scores.

The mobile app is available for iOs and Android.

Read more >

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter