torchact 0.0.2

TorchAct, collection of activation function for PyTorch.

torchact

TorchAct, collection of activation function for PyTorch.

---

Quick Start

import torch
import torch.nn as nn
from torchact import ReLU

model = nn.Sequential(
    nn.Linear(5, 3),
    ReLU(),
    nn.Linear(3, 1)
)

dummy = torch.rand(1, 5)
print(model(dummy))

Installation

pip install torchact

How to Contribute

Thanks for your contribution!

There are several steps for contributing.

0. Install library using requirements.txt
1. Write your code in torchact folder.
2. Add your module in __init__.py (__version__ cannot be changed. It will be decided later.)

For example.

from .your_module import Your_Module
__all__ = ("ReLU", "SinLU", "Softmax", "Your_Module")

3. Add your module in test_activation_function.py

For example.

from torchact import Your_Module
test_model.add_module("Your_Module", Your_Module())

4. Send a PR. Code testing happens automatically. (PYPI is upgraded by the admin himself.)