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.
AI App Predicts the Popularity of Social Media Posts
Aug 25, 2017
Discuss (1)
AI-Generated Summary
- Cornea AI applies deep learning to predict how well a photo will perform on social platforms.
- The app trains five neural networks for style transfer, color transfer, hashtag recommendation from similar popular images, hashtag recommendation from photo content, and popularity scoring.
- Training runs on GeForce GTX 1080 Ti GPUs using cuDNN-accelerated Keras and Lasagne frameworks.
- The mobile app is available for iOS and Android.
Next Steps
- Download the deep learning tools to explore the frameworks used for training.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
