B
bottom-up-attention
peteanderson80/bottom-up-attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
★1.5kstars
Jupyter Notebook
MIT
Updated: 2w ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Jupyter Notebook, focusing on caffe and captioning-images
Who made it?Maintained by peteanderson80 team, 1.5K⭐ on GitHub, #831 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the peteanderson80 team identified the need for better caffe solutions. bottom-up-attention was created to simplify captioning-images workflows.
What can it do?Key use cases: faster-rcnn, image-captioning, mscoco
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/peteanderson80/bottom-up-attention | 官网 http://panderson.me/up-down-attention/
🔗 github.com/peteanderson80/bottom-up-attention | 官网 http://panderson.me/up-down-attention/
Topics
caffecaptioning-imagesfaster-rcnnimage-captioningmscocomscoco-datasetvisual-question-answeringvqa