CUDA Implementation of T-SNE with Python bindings
Project description
tsnecuda provides an optimized CUDA implementation of the T-SNE algorithm by L Van der Maaten. tsnecuda is able to compute the T-SNE of large numbers of points up to 1200 times faster than other leading libraries, and provides simple python bindings with a SKLearn style interface:
#!/usr/bin/env python from tsnecuda import TSNE embeddedX = TSNE(n_components=2).fit_transform(X)
For more information, check out the repository at https://github.com/rmrao/tsne-cuda.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
| Filename, size | File type | Python version | Upload date | Hashes |
|---|---|---|---|---|
| Filename, size tsnecuda-0.1.1-py3-none-any.whl (16.1 MB) | File type Wheel | Python version py3 | Upload date | Hashes View |
| Filename, size tsnecuda-0.1.1.tar.gz (16.1 MB) | File type Source | Python version None | Upload date | Hashes View |
