pytorch
  1. pytorch-implementation-of-dnn
PreviousNext

Implementation of DNN - ( Deep Neural Network with PyTorch )

Heading h2

Syntax

import torch
import torch.nn as nn
import torch.optim as optim

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.fc1 = nn.Linear(10, 100)
        self.fc2 = nn.Linear(100, 50)
        self.out = nn.Linear(50, 1)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = torch.sigmoid(self.out(x))
        return x

criterion = nn.BCELoss()

optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

Example

import torch
import torch.nn as nn
import torch.optim as optim

class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.fc1 = nn.Linear(2, 4)
        self.fc2 = nn.Linear(4, 2)
        self.out = nn.Linear(2, 1)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = torch.sigmoid(self.out(x))
        return x

model = MyModel()

X = torch.tensor([[0, 0], [0, 1], [1, 0], [1, 1]], dtype=torch.float)
y = torch.tensor([[0], [1], [1], [0]], dtype=torch.float)

criterion = nn.BCELoss()

optimizer = optim.SGD(model.parameters(), lr=0.1)

for epoch in range(10000):
    optimizer.zero_grad()
    output = model(X)
    loss = criterion(output, y)
    loss.backward()
    optimizer.step()

print(model(X))

Output

tensor([[0.0279],
        [0.9644],
        [0.9626],
        [0.0447]], grad_fn=<SigmoidBackward>)

Explanation

In this example, we're using PyTorch to implement a deep neural network. The neural network has two hidden layers with 4 and 2 neurons respectively and uses the sigmoid activation function for the output layer.

We're using the binary cross-entropy loss function and the stochastic gradient descent optimizer to train the model.

The neural network is trained on a small dataset of 4 input samples and their corresponding binary output values. The model is trained for 10000 epochs and finally tested on the same input samples.

Use

You can use this code as a starting point for implementing your own neural networks in PyTorch. The example demonstrates how to define the neural network architecture, create an instance of the model, define the loss function and optimizer, and train the model.

Important Points

  • PyTorch is a powerful deep learning framework that allows you to define and train neural networks
  • The example demonstrates how to define a deep neural network with PyTorch and train it using stochastic gradient descent
  • The example also shows how to define the loss function and evaluate the output of the neural network on test data

Summary

In conclusion, this example provides a simple and easy-to-understand implementation of a deep neural network with PyTorch. While the example is small and simple, it provides a solid foundation for building more complex neural networks. PyTorch is a powerful deep learning framework with a lot of versatility and flexibility, and you can use it to build a wide range of deep learning models for various applications.

Backpropagation ProcessTesting of DNN model
Published on: