Data

Tools

Indexes

Applications

Experiments

Open Source Science

torch_activation

Torch-activation, a library of activation functions for PyTorch library

https://github.com/hdmquan/torch_activation

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.7%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

Torch-activation, a library of activation functions for PyTorch library

Basic Info
Statistics
  • Stars: 26
  • Watchers: 3
  • Forks: 7
  • Open Issues: 2
  • Releases: 8
Created almost 3 years ago · Last pushed 11 months ago
Metadata Files
Readme License Citation Roadmap

README.md

PyTorch Activations

PyTorch Activations is a collection of activation functions for the PyTorch library. This project aims to provide an easy-to-use solution for experimenting with different activation functions or simply adding variety to your models.

6 sample activation functions and its derivatives

Installation

You can install PyTorch Activations using pip:

bash $ pip install torch-activation

Usage

To use the activation functions, import them from torch_activation. Here's an example:

```python import torch_activation as tac

m = tac.ShiLU(inplace=True) x = torch.rand(16, 3, 384, 384) m(x) ```

Or in nn.Sequential:

```python import torch import torch.nn as nn import torch_activation as tac

class Net(nn.Module): def init(self): super(Net, self).init() self.net = nn.Sequential( nn.Conv2d(64, 32, 2), tac.DELU(), nn.ConvTranspose2d(32, 64, 2), tac.ReLU(inplace=True), )

def forward(self, x):
    return self.net(x)

```

Activation functions can be imported directly from the package, such as torch_activation.CoLU, or from submodules, such as torch_activation.classical.CoLU or torch_activation.classical.sigmoid_weighted.CoLU.

To learn more about usage and the comprehended list of available functions, please refer to Documentation

We hope you find PyTorch Activations useful for your experimentation and model development. Enjoy exploring different activation functions!

Contact

Alan Huynh - LinkedIn - hdmquan@outlook.com

Project Link: https://github.com/hdmquan/torch_activation

Documentation Link: https://torch-activation.readthedocs.io

PyPI Link: https://pypi.org/project/torch-activation/

Owner

  • Name: Alan Huynh
  • Login: hdmquan
  • Kind: user
  • Location: Melbourne, Australia

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this library, please cite it as below."
authors:
- family-names: "Huynh"
  given-names: "Alan"
title: "Torch Activation"
version: 0.4.0
license: MIT
license-url: "https://github.com/hdmquan/torch_activation/blob/main/LICENSE"
date-released: 2023-17-05
url: "https://github.com/hdmquan/torch_activation"

GitHub Events

Total
  • Create event: 9
  • Issues event: 5
  • Release event: 3
  • Watch event: 17
  • Delete event: 2
  • Member event: 1
  • Issue comment event: 11
  • Push event: 103
  • Pull request review event: 7
  • Pull request event: 35
  • Fork event: 4
Last Year
  • Create event: 9
  • Issues event: 5
  • Release event: 3
  • Watch event: 17
  • Delete event: 2
  • Member event: 1
  • Issue comment event: 11
  • Push event: 103
  • Pull request review event: 7
  • Pull request event: 35
  • Fork event: 4

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 2
  • Total pull requests: 36
  • Average time to close issues: 3 days
  • Average time to close pull requests: 1 day
  • Total issue authors: 1
  • Total pull request authors: 5
  • Average comments per issue: 0.5
  • Average comments per pull request: 0.61
  • Merged pull requests: 34
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 2
  • Pull requests: 35
  • Average time to close issues: 3 days
  • Average time to close pull requests: 1 day
  • Issue authors: 1
  • Pull request authors: 5
  • Average comments per issue: 0.5
  • Average comments per pull request: 0.63
  • Merged pull requests: 33
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • hdmquan (2)
Pull Request Authors
  • hdmquan (21)
  • enessinanparildi (10)
  • AnnNguyen975 (2)
  • dipplestix (2)
  • Baran-phys (1)
Top Labels
Issue Labels
enhancement (1)
Pull Request Labels
enhancement (3)

Dependencies

.github/workflows/workflows.yml actions
  • actions/checkout v3 composite
  • pypa/gh-action-pypi-publish release/v1 composite
docs/requirements.txt pypi
  • Babel *
  • Sphinx *
  • imagesize *
  • jinja2 *
  • plotly *
  • psutil *
  • readme-renderer *
  • sphinx-rtd-theme *
  • sphinxcontrib-napoleon *
  • torch *
pyproject.toml pypi
  • python >=3.6
  • torch >=1.0.0
requirements.txt pypi
  • kaleido *
  • numpy *
  • plotly *
  • torch >=1.1.0
setup.py pypi
  • torch *