NVIDIA/MinkowskiEngine
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
This library helps deep learning researchers and practitioners build neural networks that efficiently process spatially sparse data, common in high-dimensional tasks like 3D perception. It takes in sparse tensors representing data such as 3D point clouds or volumes and outputs processed sparse tensors, enabling tasks like semantic segmentation, object classification, and 3D reconstruction. This is used by machine learning engineers working on advanced computer vision and 3D data analysis.
2,883 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing neural networks that need to efficiently handle large, sparse, high-dimensional data, especially in 3D applications.
Not ideal if your data is dense or low-dimensional, or if you are not working with deep learning models.
Stars
2,883
Forks
461
Language
Python
License
—
Category
Last pushed
Mar 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/MinkowskiEngine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX