AlexHex7/Non-local_pytorch
PyTorch implementation of Non-local Neural Block with multiple attention variants and visualization tools.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of the Non-local Neural Network block from the 2017 paper. It includes multiple variants of the attention mechanism (Gaussian, embedded Gaussian, concatenation, dot product) and supports automatic mixed precision training. The project includes training scripts for MNIST and tools to visualize non-local attention maps.
Frequently asked
- What is AlexHex7/Non-local_pytorch?
- PyTorch implementation of Non-local Neural Block with multiple attention variants and visualization tools.
- Is Non-local_pytorch open source?
- Yes — AlexHex7/Non-local_pytorch is open source, released under the Apache-2.0 license.
- What language is Non-local_pytorch written in?
- AlexHex7/Non-local_pytorch is primarily written in Python.
- How popular is Non-local_pytorch?
- AlexHex7/Non-local_pytorch has 1.6k stars on GitHub.
- Where can I find Non-local_pytorch?
- AlexHex7/Non-local_pytorch is on GitHub at https://github.com/AlexHex7/Non-local_pytorch.