vacancy/AdvancedIndexing-PyTorch

(Batched) advanced indexing for PyTorch.

29
/ 100
Experimental

This tool helps machine learning engineers and researchers efficiently extract specific data points or sections from large PyTorch tensors. You provide your PyTorch tensor and a set of instructions (indices) for selecting data, and it returns the precise sub-tensor you need, even when those selection instructions vary across different 'batches' of your data. It's designed for those working with multi-dimensional data in deep learning models.

No commits in the last 6 months.

Use this if you need to perform complex, varying data selection (advanced indexing) on multi-dimensional PyTorch tensors, especially when dealing with batches where each item in the batch requires a different indexing operation.

Not ideal if your indexing needs are simple, you only work with basic Python lists or NumPy arrays, or you require boolean-based indexing across your batches.

deep-learning machine-learning-engineering data-preprocessing tensor-operations neural-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

53

Forks

2

Language

Python

License

MIT

Last pushed

Dec 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/vacancy/AdvancedIndexing-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.