معرفی شرکت ها
echoAI-0.1.3
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
Python package containing all custom and SOTA mathematical backend algorithms used in Machine Learning.
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | echoAI-0.1.3 |
| نام | echoAI |
| نسخه کتابخانه | 0.1.3 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | Diganta Misra and Aleksandra Deis |
| ایمیل نویسنده | mishradiganta91@gmail.com |
| آدرس صفحه اصلی | https://github.com/digantamisra98/Echo |
| آدرس اینترنتی | https://pypi.org/project/echoAI/ |
| مجوز | - |
<p align="left">
<img width="270" src="https://github.com/digantamisra98/Echo/raw/master/Observations/logo_transparent.png">
</p>
[](LICENSE)
# Echo-AI
Python package containing all mathematical backend algorithms used in Machine Learning.
The full documentation for Echo is provided [here](https://echo-ai.readthedocs.io/en/latest/).
## Table of Contents
* [About the Project](#about)
* [Activation Functions](#activation-functions)
* [Repository Structure](#repository-structure)
* [Setup Instructions](#setup-instructions)
## 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](https://pytorch.org/), [Keras](https://keras.io/) and
[TensorFlow](https://www.tensorflow.org/).
### 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 |  | ✅ | ✅ | ✅ |🕑|
|2| [Swish](https://arxiv.org/pdf/1710.05941.pdf) |  | ✅ | ✅ | ✅ |🕑|
|3| [ESwish](https://arxiv.org/abs/1801.07145) |  | ✅ | ✅| ✅ |🕑|
|4| [Aria2](https://arxiv.org/abs/1805.08878) |  |✅| ✅ | ✅ |🕑|
|5| [ELiSH](https://arxiv.org/pdf/1808.00783.pdf) |  | ✅ | ✅ | ✅ |🕑|
|6| [HardELiSH](https://arxiv.org/pdf/1808.00783.pdf) |  | ✅ | ✅ | ✅ |🕑|
|7| [Mila](https://github.com/digantamisra98/Mila) |  | ✅ | ✅ | ✅ |🕑|
|8| [SineReLU](https://medium.com/@wilder.rodrigues/sinerelu-an-alternative-to-the-relu-activation-function-e46a6199997d) |  | ✅ | ✅ | ✅ |🕑|
|9| [Flatten T-Swish](https://arxiv.org/pdf/1812.06247.pdf) |  | ✅ | ✅ | ✅ |🕑|
|10| [SQNL](https://ieeexplore.ieee.org/document/8489043) |  | ✅ | ✅ | ✅ |🕑|
|11| [ISRU](https://arxiv.org/pdf/1710.09967.pdf) |  | ✅ | ✅ | ✅ |🕑|
|12| [ISRLU](https://arxiv.org/pdf/1710.09967.pdf) |  | ✅ | ✅ | ✅ |🕑|
|13| Bent's identity |  | ✅ | ✅ | ✅ |🕑|
|14| [Soft Clipping](https://arxiv.org/pdf/1810.11509.pdf) |  | ✅ | ✅ | ✅ |🕑 |
|15| [SReLU](https://arxiv.org/pdf/1512.07030.pdf) |  | ✅ | ✅ | ✅ |🕑|
|15| [BReLU](https://arxiv.org/pdf/1709.04054.pdf) |  | 🕑 | ✅ | ✅ |🕑|
|16| [APL](https://arxiv.org/pdf/1412.6830.pdf) |  | 🕑 | ✅ | ✅ |🕑|
|17| [Soft Exponential](https://arxiv.org/pdf/1602.01321.pdf) |  | ✅| ✅ | ✅ |🕑|
|18| [Maxout](https://arxiv.org/pdf/1302.4389.pdf) |  | 🕑 | ✅ | ✅ |🕑|
|19| [Mish](https://github.com/digantamisra98/Mish) |  | ✅ | ✅ | ✅ |🕑|
|20| [Beta Mish](https://github.com/digantamisra98/Beta-Mish) | | ✅ | ✅ | ✅ |🕑|
|21| [RReLU](https://arxiv.org/pdf/1505.00853.pdf) | | 🕑 | ⬜ | 🕑 |🕑|
|22| [CELU](https://arxiv.org/pdf/1704.07483.pdf) | | ✅ | ⬜ | ✅ |🕑|
|23| ReLU6 | | ✅ | ⬜ | 🕑 |🕑|
|24| HardTanh | | ✅ | ⬜ | ✅ |🕑|
|25| [GLU](https://arxiv.org/pdf/1612.08083.pdf) | | 🕑 | ⬜ | 🕑 | 🕑|
|26| LogSigmoid | | ✅ | ⬜ | ✅ |🕑 |
|27| TanhShrink | | ✅ | ⬜ | ✅ | 🕑|
|28| HardShrink | | ✅ | ⬜ | ✅ |🕑 |
|29| SoftShrink | | ✅ | ⬜ | ✅ | 🕑|
|30| SoftMin | | ✅ | ⬜ | ✅ |🕑 |
|31| LogSoftmax | | ✅ | ⬜ | ✅ | 🕑|
|32| [Gumbel-Softmax](https://arxiv.org/pdf/1611.01144.pdf) | | 🕑 | ⬜ | 🕑 |🕑 |
## Repository Structure
The repository has the following structure:
```python
- 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](/Smoke_tests) folder.
You can use activation functions from echoAI as simple as this:
```python
# 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)
```
نحوه نصب
نصب پکیج whl echoAI-0.1.3:
pip install echoAI-0.1.3.whl
نصب پکیج tar.gz echoAI-0.1.3:
pip install echoAI-0.1.3.tar.gz