Image Captioning with Deep Learning and Attention Mechanism in PyTorch

Описание: This is an implementation of the paper: Show, Attend and Tell: https://arxiv.org/pdf/1502.03044.pdf

I packaged the model inside a small web app for demo purposes where you can see live image captioning with visual attention mechanism to highlight the areas where the model focuses when generating each word.

The model is implemented in PyTorch here: https://github.com/sgrvinod/a-PyTorch... - you can reuse it.

Follow me at:
Medium:   / ahmedbesbes  
My blog: https://ahmedbesbes.com
Twitter:   / ahmed_besbes_  
Github: https://github.com/ahmedbesbes
Linkedin:   / ahmed-besbes-99a91661  

and consider subscribing to this channel for more content.