Skip to main content

PyTorch Code for Simple Neural Networks for MNIST Dataset

PyTorch Code for Simple Neural Networks for MNIST Dataset

PyTorch Introduction

To Install PyTorch in Linux (Ubuntu), here is the step:

$ sudo apt install python3-pip python3 python3-dev

$ pip3 install torch torchvision torchaudio notebook

MNIST Dataset (0 to 9 handwritten characters) as given below

MNIST Dataset

Given the dataset of MNIST, do the accuracy analysis of the dataset based on the following hyperparameters using Deep Learning with PyTorch

1. Number of epochs is 4,5,6 and 7
2. batch_size is 64 and 128
3. Number of Hidden layers is 1 and 2
4. Learning rate is 0.001, 0.002 and 0.003
Compute the accuracy in each case.

Run the following code either using the Jupyter Notebook or Google Colab.

To run the notebook, the command is 

$ python3 -m notebook

import torch
import torch.nn as nn
import torch.optim as optim
from import DataLoader, TensorDataset
from torchvision import datasets, transforms
from torch.autograd import Variable

# Define a simple neural network model
class SimpleNN(nn.Module):
 def __init__(self, input_size, num_hidden_layers, hidden_size, output_size):
  super(SimpleNN, self).__init__()
  self.flatten = nn.Flatten()
  self.hidden_layers = nn.ModuleList([nn.Linear(input_size if i == 0 else hidden_size, hidden_size) for i in range(num_hidden_layers)])
  self.output_layer = nn.Linear(hidden_size, output_size)
  self.relu = nn.ReLU()
  self.softmax = nn.Softmax(dim=1)

 def forward(self, x):
  x = self.flatten(x)
  for layer in self.hidden_layers:
   x = self.relu(layer(x))
  x = self.output_layer(x)
  x = self.softmax(x)
  return x

# Load and preprocess MNIST data using PyTorch
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,),
train_dataset = datasets.MNIST('./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST('./data', train=False, download=True, transform=transform)
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

# Define function to create and train the PyTorch model
def create_and_train_model(num_epochs, batch_size, num_hidden_layers, learning_rate):
 input_size = 28 * 28
 hidden_size = 128
 output_size = 10
 model = SimpleNN(input_size, num_hidden_layers, hidden_size, output_size)
 criterion = nn.CrossEntropyLoss()
 optimizer = optim.Adam(model.parameters(), lr=learning_rate)

 for epoch in range(num_epochs):
  for data, labels in train_loader:
    data, labels = Variable(data), Variable(labels)
    outputs = model(data)
    loss = criterion(outputs, labels)

 # Evaluate and return the accuracy
 correct = 0
 total = 0
 with torch.no_grad():
  for data, labels in test_loader:
    data, labels = Variable(data), Variable(labels)
    outputs = model(data)
    _, predicted = torch.max(, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum().item()
 accuracy = correct / total
 return accuracy

# Define hyperparameters
num_epochs_list = [4, 5, 6, 7]
batch_size_list = [64, 128]
num_hidden_layers_list = [1, 2]
learning_rate_list = [0.001, 0.002, 0.003]

# Perform the analysis
for num_epochs in num_epochs_list:
  for batch_size in batch_size_list:
    for num_hidden_layers in num_hidden_layers_list:
      for learning_rate in learning_rate_list:
        print(f"Epochs: {num_epochs}, Batch Size: {batch_size}, Hidden Layers: {num_hidden_layers}, Learning Rate: {learning_rate}")
        accuracy = create_and_train_model(num_epochs, batch_size, num_hidden_layers,
        print(f"Accuracy: {accuracy}\n") 

The following is the output we got from Google Colab 

Simple Neural Network using PyTorch


Popular posts from this blog

Installing ns3 in Ubuntu 22.04 | Complete Instructions

In this post, we are going to see how to install ns-3.36.1 in Ubuntu 22.04. You can follow the video for complete details Tools used in this simulation: NS3 version ns-3.36.1  OS Used: Ubuntu 22.04 LTS Installation of NS3 (ns-3.36.1) There are some changes in the ns3 installation procedure and the dependencies. So open a terminal and issue the following commands Step 1:  Prerequisites $ sudo apt update In the following packages, all the required dependencies are taken care and you can install all these packages for the complete use of ns3. $ sudo apt install g++ python3 python3-dev pkg-config sqlite3 cmake python3-setuptools git qtbase5-dev qtchooser qt5-qmake qtbase5-dev-tools gir1.2-goocanvas-2.0 python3-gi python3-gi-cairo python3-pygraphviz gir1.2-gtk-3.0 ipython3 openmpi-bin openmpi-common openmpi-doc libopenmpi-dev autoconf cvs bzr unrar gsl-bin libgsl-dev libgslcblas0 wireshark tcpdump sqlite sqlite3 libsqlite3-dev  libxml2 libxml2-dev libc6-dev libc6-dev-i386 libclang-dev llvm-

Installation of NS2 (ns-2.35) in Ubuntu 20.04

Installation of NS2 (ns-2.35) in Ubuntu 20.04 LTS Step 1: Install the basic libraries like      $] sudo apt install build-essential autoconf automake libxmu-dev Step 2: install gcc-4.8 and g++-4.8 open the file using sudo mode $] sudo nano /etc/apt/sources.list Include the following line deb bionic main universe $] sudo apt update $] sudo apt install gcc-4.8 g++-4.8 Step 3:  Unzip the ns2 packages to home folder $] tar zxvf ns-allinone-2.35.tar.gz $] cd ns-allinone-2.35/ns-2.35 Modify the following make files. ~ns-2.35/ Change @CC@ to gcc-4.8 change @CXX@ to g++-4.8 ~nam-1.15/ ~xgraph-12.2/ ~otcl-1.14/ Change in all places  @CC@ to gcc-4.8 @CPP@ or @CXX@ to g++-4.8 open the file: ~ns-2.35/linkstate/ls.h Change at the Line no 137  void eraseAll() { erase(baseMap::begin(), baseMap::end()); } to This void eraseAll() { this->erase(baseMap::begin(), baseMap::end()); } All changes made Step 4: Open a new termi

Installation of NS2 in Ubuntu 22.04 | NS2 Tutorial 2

NS-2.35 installation in Ubuntu 22.04 This post shows how to install ns-2.35 in Ubuntu 22.04 Operating System Since ns-2.35 is too old, it needs the following packages gcc-4.8 g++-4.8 gawk and some more libraries Follow the video for more instructions So, here are the steps to install this software: To download and extract the ns2 software Download the software from the following link Extract it to home folder and in my case its /home/pradeepkumar (I recommend to install it under your home folder) $ tar zxvf ns-allinone-2.35.tar.gz or Right click over the file and click extract here and select the home folder. $ sudo apt update $ sudo apt install build-essential autoconf automake libxmu-dev gawk To install gcc-4.8 and g++-4.8 $ sudo gedit /etc/apt/sources.list make an entry in the above file deb bionic main universe $ sudo apt update Since, it&#