esceptico/perceiver-io
Unofficial implementation of Perceiver IO
This is a developer's tool for implementing the Perceiver IO deep learning architecture. It provides the building blocks for creating models that can process various types of structured input data and produce structured outputs. A machine learning engineer or researcher would use this to build advanced neural network models for diverse tasks.
128 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher building models that need to flexibly handle different input data structures and generate specific structured outputs.
Not ideal if you are looking for an out-of-the-box solution for a specific problem like image classification or natural language processing without custom model development.
Stars
128
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jun 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/esceptico/perceiver-io"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models