salesforce/LAVIS
LAVIS is a comprehensive library for multimodal deep learning, including image captioning, visual question answering, and more.
Jupyter Notebook
AI & Machine Learning
Vision-Language Transformer
BSD-3-Clause
11.2K
Stars
1.1K
Forks
Aug 24, 2022
Created
Nov 18, 2024
Last Updated
Project Analytics
Stars Growth (1 Month)
+25
+0.2% change
Avg Daily Growth (1 Month)
+0.9
stars per day
Fork/Star Ratio (All Time)
9.8%
Normal engagement
Lifetime Growth
8.7
stars/day over 1.3K days
Stars Over Time
Forks Over Time
Open Issues Over Time
Pull Requests Over Time
Commits Over Time
Topics
AI-Generated Tags
deep-learning
multimodal-learning
vision-language
image-captioning
visual-question-answering
Similar Projects
EbookFoundation/free-programming-books
Free programming books repository with AI-powered features
383.6K
Python
jwasham/coding-interview-university
A comprehensive computer science study plan for software engineers, with a focus on coding interviews and AI-related topics.
337.6K
vinta/awesome-python
Awesome Python framework and resource collection
285.7K
Python
openclaw/openclaw
Personal AI assistant for messaging platforms, self-hosted and multi-channel
265.0K
TypeScript
Comments (0)
Sign in to leave a comment or vote
Sign InNo comments yet. Be the first to comment!
Stay in the loop
Get weekly updates on trending AI coding tools and projects.