Metadata-Version: 2.1
Name: gradients
Version: 0.0.2
Summary: Gradient Checker for Custom built PyTorch Models
Home-page: https://github.com/Saran-nns/gradients
Author: Saranraj Nambusubramaniyan
Author-email: saran_nns@hotmail.com
License: OSI Approved :: MIT License
Description: <a href="url"><img src="https://raw.githubusercontent.com/Saran-nns/gradients/master/imgs/LOGO.jpg"></a>
        ## Build your deep learning models with confidence
        
        Medium article is under work
        
        [![Build Status](https://travis-ci.com/Saran-nns/gradients.svg?branch=main)](https://travis-ci.com/Saran-nns/gradients)
        [![codecov](https://codecov.io/gh/Saran-nns/gradients/branch/main/graph/badge.svg)](https://codecov.io/gh/Saran-nns/gradients)
        [![PyPI version](https://badge.fury.io/py/gradients.svg)](https://badge.fury.io/py/gradients)
        [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
        ![PyPI - Downloads](https://img.shields.io/pypi/dm/gradients.svg)
        [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
        
        Gradients provide a unit test function to perform gradient checking on your deep learning models. It uses centered finite difference approximation to check the difference between analytical and numerical gradients and report if the check fails on any parameters of your model. Currently the library supports only PyTorch models built with custom layers, custom loss functions, activation functions and any neural network function subclassing `AutoGrad`.
        
        Optimizing deep learning models is a two step process:
        
        1. Compute gradients with respect to parameters
        
        2. Update the parameters given the gradients
            
        In PyTorch, step 1 is done by the type-based automatic differentiation system `torch.nn.autograd` and 2 by the package implementing optimization algorithms `torch.optim`. Using  them, we can develop fully customized deep learning models with `torch.nn.Module` and test them using `Gradients` as follows;
        
        ### Activation function with backward
        
        ```python
        class MySigmoid(torch.autograd.Function):
        
            @staticmethod
            def forward(ctx, input):
                output = ctx.save_for_backward(output)
                ctx.save_for_backward(output)
                return output
        
            @staticmethod
            def backward(ctx, grad_output):
                input, = ctx.saved_tensors
                return input*(1-input)*grad_output
        ```
        
        ### Loss function with autograd backward
        
        ```python
        class MSELoss(torch.autograd.Function):
        
            @staticmethod
            def forward(ctx, y_pred, y):
                ctx.save_for_backward(y_pred, y)
                return ((y_pred-y)**2).sum()/y_pred.shape[0]
        
            @staticmethod
            def backward(ctx, grad_output):
                y_pred, y = ctx.saved_tensors
                grad_input = 2 * (y_pred-y)/y_pred.shape[0]
                return grad_input, None
        ```
        ### Pytorch Model
        
        ```python
        class MyModel(torch.nn.Module):
            def __init__(self,D_in, D_out):
                super(MyModel,self).__init__()
                self.w1 = torch.nn.Parameter(torch.randn(D_in, D_out), requires_grad=True)
            def forward(self,x):
                y_pred = mysigmoid(x.mm(self.w1))
                return y_pred
        ```
        ### Optimizer
        ```python
        class SGD(torch.optim.Optimizer):
            """Reference: http://pytorch.org/docs/master/_modules/torch/optim/sgd.html#SGD"""
            def __init__(self, params, lr=1e-3):
                defaults = dict(lr=lr)
                super(SGD,self).__init__(params,defaults)
        
            def __setstate__(self, state):
                super(SGD, self).__setstate__(state)
        
            def step(self, closure=None):
        
                loss = None
                if closure is not None:
                    loss = closure()
        
                for group in self.param_groups:
        
                    for p in group['params']:
                        if p.grad is None:
                            continue
                        d_p = p.grad.data
                        p.data.add_(-group['lr'], d_p)
                return loss
        ```
        TODO
        ### Instantiate, gradcheck and train the model
        
        
        
        
        
Keywords: PyTorch,Artificial Neural Networks,Gradients,BackPropagation,Machine Learning
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/markdown
