Ending2015a/hash-grid-encoding
Pure PyTorch implementation of Nvidia's hash grid encoding: https://nvlabs.github.io/instant-ngp/
This tool helps machine learning developers efficiently process and represent high-resolution spatial data, like gigapixel images or 3D models. It takes raw spatial coordinates (e.g., pixel locations, 3D points) and transforms them into a richer, more compact representation, which can then be fed into a neural network. This is for machine learning engineers working on tasks involving detailed spatial information.
No commits in the last 6 months.
Use this if you need to work with extremely large images or complex 3D scenes in your PyTorch neural networks and want to improve training efficiency and memory usage.
Not ideal if you are not working with PyTorch, or if your tasks do not involve processing high-dimensional spatial data.
Stars
92
Forks
9
Language
Python
License
MIT
Category
Last pushed
Sep 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ending2015a/hash-grid-encoding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)