Skip to main content

Python package containing all custom and SOTA mathematical backend algorithms used in Machine Learning.

Project description

Donate

Echo-AI

Python package containing all mathematical backend algorithms used in Machine Learning. The full documentation for Echo is provided here.

Table of Contents

About

Echo-AI Package is created to provide an implementation of the most promising mathematical algorithms, which are missing in the most popular deep learning libraries, such as PyTorch, Keras and TensorFlow.

Activation Functions

The package contains implementation for following activation functions (✅ - implemented functions, 🕑 - functions to be implemented soon, :white_large_square: - function is implemented in the original deep learning package):

# Function Equation Keras PyTorch TensorFlow-Keras TensorFlow - Core
1 Weighted Tanh equation ✅ ✅ ✅ 🕑
2 Swish equation ✅ ✅ ✅ 🕑
3 ESwish equation ✅ ✅ ✅ 🕑
4 Aria2 equation ✅ ✅ ✅ 🕑
5 ELiSH equation ✅ ✅ ✅ 🕑
6 HardELiSH equation ✅ ✅ ✅ 🕑
7 Mila equation ✅ ✅ ✅ 🕑
8 SineReLU equation ✅ ✅ ✅ 🕑
9 Flatten T-Swish equation ✅ ✅ ✅ 🕑
10 SQNL equation ✅ ✅ ✅ 🕑
11 ISRU equation ✅ ✅ ✅ 🕑
12 ISRLU equation ✅ ✅ ✅ 🕑
13 Bent's identity equation ✅ ✅ ✅ 🕑
14 Soft Clipping equation ✅ ✅ ✅ 🕑
15 SReLU equation ✅ ✅ ✅ 🕑
15 BReLU equation 🕑 ✅ ✅ 🕑
16 APL equation 🕑 ✅ ✅ 🕑
17 Soft Exponential equation ✅ ✅ ✅ 🕑
18 Maxout equation 🕑 ✅ ✅ 🕑
19 Mish equation ✅ ✅ ✅ 🕑
20 Beta Mish equation ✅ ✅ ✅ 🕑
21 RReLU equation 🕑 ⬜ 🕑 🕑
22 CELU equation ✅ ⬜ ✅ 🕑
23 ReLU6 equation ✅ ⬜ 🕑 🕑
24 HardTanh equation ✅ ⬜ ✅ 🕑
25 GLU equation 🕑 ⬜ 🕑 🕑
26 LogSigmoid equation ✅ ⬜ ✅ 🕑
27 TanhShrink equation ✅ ⬜ ✅ 🕑
28 HardShrink equation ✅ ⬜ ✅ 🕑
29 SoftShrink equation ✅ ⬜ ✅ 🕑
30 SoftMin equation ✅ ⬜ ✅ 🕑
31 LogSoftmax equation ✅ ⬜ ✅ 🕑
32 Gumbel-Softmax 🕑 ⬜ 🕑 🕑

Repository Structure

The repository has the following structure:

- echoAI # main package directory
| - Activation # sub-package containing activation functions implementation
| |- Torch  # sub-package containing implementation for PyTorch
| | | - functional.py # script which contains implementation of activation functions
| | | - weightedTanh.py # activation functions wrapper class for PyTorch
| | | - ... # PyTorch activation functions wrappers
| |- Keras  # sub-package containing implementation for Keras
| | | - custom_activations.py # script which contains implementation of activation functions
| |- TF_Keras  # sub-package containing implementation for Tensorflow-Keras
| | | - custom_activation.py # script which contains implementation of activation functions
| - __init__.py

- Observations # Folder containing other assets

- docs # Sphinx documentation folder

- LICENSE # license file
- README.md
- setup.py # package setup file
- Smoke_tests # folder, which contains scripts with demonstration of activation functions usage
- Unit_tests # folder, which contains unit test scripts

Setup Instructions

To install echoAI package from PyPI run the following command:

$ pip install echoAI

Code Examples:

Sample scripts are provided in Smoke_tests folder. You can use activation functions from echoAI as simple as this:

# import PyTorch
import torch

# import activation function from echoAI
from echoAI.Activation.Torch.mish import Mish

# apply activation function
mish = Mish()
t = torch.tensor(0.1)
t_mish = mish(t)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for echoAI, version 0.1.3
Filename, size File type Python version Upload date Hashes
Filename, size echoAI-0.1.3-py3-none-any.whl (37.3 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size echoAI-0.1.3.tar.gz (20.5 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page