willGuimont/learnable_fourier_positional_encoding
Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding
This helps researchers working with multi-dimensional spatial data, such as images, 3D scans, or even higher-dimensional scientific measurements, to improve how their machine learning models understand the position of different data points. It takes raw spatial coordinates and transforms them into a richer 'positional encoding' that makes it easier for neural networks to learn complex relationships based on location. Scientists and engineers in fields like medical imaging, computational physics, or robotics who use deep learning on spatial data would find this useful.
No commits in the last 6 months. Available on PyPI.
Use this if you are training deep learning models on multi-dimensional spatial data and need a more effective way for your model to capture and utilize positional information.
Not ideal if your data does not have inherent spatial dimensions or if you are not working with deep learning models that benefit from explicit positional encoding.
Stars
55
Forks
9
Language
Python
License
MIT
Category
Last pushed
Sep 30, 2024
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/willGuimont/learnable_fourier_positional_encoding"
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.
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models