Merge pull request #30 from bhavnicksm/main

Update README; Add ToC + Update supported

README.md

@@ -2,7 +2,6 @@
 
 # Nadir
 
-
 ![PyPI - Downloads](https://img.shields.io/pypi/dm/nadir)
 ![GitHub commit activity](https://img.shields.io/github/commit-activity/m/Dawn-Of-Eve/nadir)
 ![GitHub Repo stars](https://img.shields.io/github/stars/Dawn-Of-Eve/nadir?style=social)
@@ -12,34 +11,33 @@
 
 PyTorch is a popular machine learning framework that provides a flexible and efficient way of building and training deep neural networks. This library, Nadir, is built on top of PyTorch to provide high-performing general-purpose optimisation algorithms.  
 
-:warning: ***Currently in Developement Beta version with every update having breaking changes; user discreation and caution advised!*** :warning:
-
-## Supported Optimisers
-
-| Optimiser 	| Paper 	                                            |
-|:---------:	|:-----:	                                            |
-|  **SGD**  	| https://paperswithcode.com/method/sgd                 |
-|  **Momentum** | https://paperswithcode.com/method/sgd-with-momentum   |
-|  **Adagrad** 	| https://www.jmlr.org/papers/volume12/duchi11a/duchi11a.pdf |
-|  **RMSProp** 	| https://paperswithcode.com/method/rmsprop             |
-|  **Adam**     | https://arxiv.org/abs/1412.6980v9                     |
-|  **Adamax**   | https://arxiv.org/abs/1412.6980v9                     |
-|  **Adadelta** | https://arxiv.org/abs/1212.5701v1                     |
-
+# Table of Contents
 
+- [Nadir](#nadir)
+- [Table of Contents](#table-of-contents)
+- [Installation](#installation)
+- [Simple Usage](#simple-usage)
+- [Supported Optimisers](#supported-optimisers)
+- [Acknowledgements](#acknowledgements)
+- [Citation](#citation)
 
 
-## Installation
 
-Nadir is on the PyPi packaging Index! :partying_face:
+# Installation
 
-Simply run the following command on your terminal and start using Nadir now!
+You can either choose to install from the PyPI index, in the following manner:
 
 ```bash
 $ pip install nadir
 ```
+or install from source, in the following manner:
 
-## Usage
+```bash
+$ pip install git+https://github.com/Dawn-Of-Eve/nadir.git
+```
+**Note:** Installing from source might lead to a breaking package. It is recommended that you install from PyPI itself.
+
+# Simple Usage
 
 ```python
 import nadir as nd
@@ -51,5 +49,41 @@ model = ...
 config = nd.SGDConfig(lr=learning_rate)
 optimizer = nd.SGD(model.parameters(), config)
 
+# Call the optimizer step
+optimizer.step()
 ```
 
+# Supported Optimisers
+
+| Optimiser 	| Paper 	                                            |
+|:---------:	|:-----:	                                            |
+|  **SGD**  	| https://paperswithcode.com/method/sgd                 |
+|  **Momentum** | https://paperswithcode.com/method/sgd-with-momentum   |
+|  **Adagrad** 	| https://www.jmlr.org/papers/volume12/duchi11a/duchi11a.pdf |
+|  **RMSProp** 	| https://paperswithcode.com/method/rmsprop             |
+|  **Adam**     | https://arxiv.org/abs/1412.6980v9                     |
+|  **Adamax**   | https://arxiv.org/abs/1412.6980v9                     |
+|  **AdamW**    | https://arxiv.org/abs/1711.05101v3                    |
+|  **Adadelta** | https://arxiv.org/abs/1212.5701v1                     |
+|  **AMSGrad**    | https://arxiv.org/abs/1904.09237v1                    |
+|  **RAdam**    | https://arxiv.org/abs/1908.03265v4                    |
+|  **Lion**     | https://arxiv.org/abs/2302.06675                      |
+
+# Acknowledgements
+
+We would like to thank all the amazing contributors of this project who spent so much effort making this repositary awesome! :heart:
+
+
+# Citation
+
+You can use the _Cite this repository_ button provided by Github or use the following bibtex:
+
+```bibtex
+@software{MinhasNadir,
+    title        = {{Nadir: A Library for Bleeding-Edge Optimizers in PyTorch}},
+    author       = {Minhas, Bhavnick and Kalathukunnel, Apsal},
+    year         = 2023,
+    month        = 3,
+    version      = {0.0.2}
+}
+```

src/nadir/__init__.py

@@ -21,12 +21,14 @@
 from .adam import Adam, AdamConfig
 from .adamax import Adamax, AdamaxConfig
 from .base import BaseOptimizer, BaseConfig
+from .lion import Lion, LionConfig
 from .momentum import Momentum, MomentumConfig
 from .rmsprop import RMSProp, RMSPropConfig
+from .radam import Radam, RadamConfig
 from .sgd import SGD, SGDConfig
 
 
-__version__ = "0.0.2"
+__version__ = "0.0.3"
 
 __all__ = ('Adadelta',
            'AdadeltaConfig',
@@ -35,12 +37,17 @@
            'Adam',
            'AdamConfig',
            'Adamax', 
-           'AdamaxConfig', 
+           'AdamaxConfig',
+           'Adam' 
            'BaseOptimizer',
            'BaseConfig',
+           'Lion',
+           'LionConfig',
            'Momentum',
            'MomentumConfig',
            'RMSProp',
            'RMSPropConfig',
+           'Radam',
+           'RadamConfig',
            'SGD',
            'SGDConfig')

tests/mnist.py

@@ -58,7 +58,7 @@
 
 # writing the logging args as a namespace obj
 largs = argparse.Namespace()
-largs.run_name : str = 'Nadir-Adadelta 2'
+largs.run_name : str = 'Nadir-Lion'
 largs.run_seed : str = args.seed
 
 
@@ -94,7 +94,7 @@ def forward(self, x):
         return output
 
 
-def train(args, model, device, train_loader, optimizer, epoch):
+def train(args, model, device, train_loader, oAdadeltaptimizer, epoch):
     model.train()
     for (data, target)in (pbar := tqdm(train_loader)):
         data, target = data.to(device), target.to(device)
@@ -212,13 +212,11 @@ def mnist_tester(model, optimizer=None, args = None):
     run.name = f'{largs.run_name}'
     run.config.update(args)
     run.config.update(largs)
-
 
-
     # Initialising the optimiser
     model = MNISTestNet().to(args.device)
     # config = nd.AdadeltaConfig(lr = args.learning_rate, beta_1=args.betas[0], beta_2=args.betas[1])
-    optimizer = nd.Adadelta(model.parameters())
+    optimizer = nd.Lion(model.parameters())
     #    config = AutoConfig(args.params..)
     #    optimizer = args.optimizer(config)