t-SNE pytorch Implementation with CUDA

CUDA-accelerated PyTorch implementation of the t-stochastic neighbor embedding algorithm described in Visualizing Data using t-SNE.

Installation

Requires Python 3.7

Install via Pip

pip3 install tsne-torch

Install from Source

git clone https://github.com/palle-k/tsne-pytorch.git
cd tsne-pytorch
python3 setup.py install

Usage

from tsne_torch import TorchTSNE as TSNE

X = ...  # shape (n_samples, d)
X_emb = TSNE(n_components=2, perplexity=30, n_iter=1000, verbose=True).fit_transform(X)  # returns shape (n_samples, 2)

Command-Line Usage

python3 -m tsne_torch --xfile <path> --yfile <path>

Example

This is our result compare to result of python implementation.

PyTorch result

pytorch result

python result

python result

Credit

This code highly inspired by

author's python implementation code here.

Metadata

Release files for tsne-torch 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tsne-torch 1.0.1
File	Size	Uploaded	Provenance	Actions
tsne-torch-1.0.1.tar.gz	5.3 kB	May 8, 2021	Without provenance	Details for tsne-torch-1.0.1.tar.gz

Release files / tsne-torch-1.0.1.tar.gz

Download URL	tsne-torch-1.0.1.tar.gz
Size	5.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`be65407c689a93f8dabff43da393e18fef5ea3bbd4f4119b90dcdf13fc5e4440`
BLAKE2b-256 checksum How to use checksums	`185b8353fd7baad6e55c21f71f2a068e47ac96dc032e58412a87276c39bb3868`
Upload date	May 8, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.6`

Security for tsne-torch 1.0.1

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.1 This release

May 8, 2021 1 release file No provenance

1.0.0

May 8, 2021 2 release files No provenance

tsne-torch 1.0.1