ziplab/LIT
[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"
This project provides optimized AI models for analyzing images efficiently. It takes in images and outputs classifications (e.g., 'cat,' 'dog'), detected objects with bounding boxes (e.g., 'car' at coordinates X, Y), or segmented regions (e.g., outlining a 'tree'). This tool is for AI practitioners and researchers who build or deploy computer vision systems and need high performance.
No commits in the last 6 months.
Use this if you are developing computer vision applications for image classification, object detection, or semantic segmentation and need a model that balances accuracy with computational efficiency.
Not ideal if you are looking for a plug-and-play solution without any AI model development or fine-tuning, or if your tasks do not involve processing visual data.
Stars
97
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ziplab/LIT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action