lucidrains/perceiver-pytorch
A PyTorch implementation of the Perceiver architecture, a transformer-based neural network using iterative cross-attention and latent self-attention for general perception tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of the Perceiver model from Google DeepMind, a general-purpose architecture that processes arbitrary modality inputs using iterative attention. The model uses a small set of latent queries to attend over large input arrays, avoiding the quadratic complexity of standard self-attention. It supports configurable depth, attention heads, frequency encoding, and weight tying across layers for flexible image, video, or multimodal perception tasks.
Frequently asked
- What is lucidrains/perceiver-pytorch?
- A PyTorch implementation of the Perceiver architecture, a transformer-based neural network using iterative cross-attention and latent self-attention for general perception tasks.
- Is perceiver-pytorch open source?
- Yes — lucidrains/perceiver-pytorch is open source, released under the MIT license.
- What language is perceiver-pytorch written in?
- lucidrains/perceiver-pytorch is primarily written in Python.
- How popular is perceiver-pytorch?
- lucidrains/perceiver-pytorch has 1.2k stars on GitHub.
- Where can I find perceiver-pytorch?
- lucidrains/perceiver-pytorch is on GitHub at https://github.com/lucidrains/perceiver-pytorch.