Metadata-Version: 2.1
Name: nadir
Version: 0.0.1.dev1
Summary: Nadir is a library of bleeding-edge DL optimisers built for speed and functionality in PyTorch for researchers
Author-email: Bhavnick Minhas <bhavnicksm@gmail.com>
Maintainer-email: Bhavnick Minhas <bhavnicksm@gmail.com>
License: Apache 2.0
Project-URL: Homepage, https://github.com/Dawn-Of-Eve/nadir
Project-URL: Bug Tracker, https://github.com/Dawn-Of-Eve/nadir/issues
Keywords: machine learning,optimization,adam-optimizer
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENCE

# Nadir

**Nadir** (pronounced _nay-d-ah_) is derived from the arabic word _nazir_, means the lowest point of a space and is the opposite of the word zenith. In optimisation terms, it is equivalent to the point of minima. And making the machine learning model reach that point of Nadir under optimisation is the purpose of this library.  

This library is built on top of PyTorch to provide high-performing general-purpose optimisation algorithms. 


## Supported Optimisers

| Optimiser 	| Paper 	|
|:---------:	|:-----:	|
|  **SGD**  	|       	|
|  **Adam** 	|       	|


## Installation

Currently, Nadir is not on the PyPi packaging index, so you would need to install it from source. 

To install Nadir into your python environment, paste the commands in your terminal:

```bash
$ pip install nadir
```

## Usage


```python
import nadir as nd

# some model setup here...
model = ...

# set up your Nadir optimiser
config = nd.SGDConfig(lr=learning_rate)
optimizer = nd.SGD(model.parameters(), config)

```

