Guest400123064/ezgatr
Geometric Algebra Transformer Made Easy
This is a lightweight Python library for machine learning researchers and engineers who are building advanced neural networks. It simplifies the process of creating 3D Geometric Algebra Transformers (GATr), which are particularly effective for tasks involving geometric data like point clouds. You input your 3D object data, and it outputs the processed features or predictions from your GATr model.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer developing neural networks that need to process complex 3D geometric data with high efficiency and symmetry awareness.
Not ideal if you are looking for a pre-trained model for general-purpose 3D object recognition or if you are not comfortable with advanced PyTorch model development.
Stars
17
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Guest400123064/ezgatr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SamsungSAILMontreal/nino
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
graphdeeplearning/graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to...
vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional...
snap-stanford/relgt
Relational Graph Transformer
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...