pytorch
  1. pytorch-training-of-cnn
PreviousNext

Training of CNN - ( Convolutional Neural Network in PyTorch )

Heading h2

Syntax

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

model = MyCNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

Example

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

# Define the CNN model
class MyCNN(nn.Module):
    def __init__(self):
        super(MyCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(32, 64, 3, stride=1, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x
      
# Instantiate the model
model = MyCNN()

# Define the loss criterion and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

Output

MyCNN(
  (conv1): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (fc1): Linear(in_features=3136, out_features=128, bias=True)
  (fc2): Linear(in_features=128, out_features=10, bias=True)
)

Explanation

Training a Convolutional Neural Network (CNN) in PyTorch involves defining the model architecture, specifying the loss criterion and optimizer, and iterating over the training data.

In the example above, we defined a simple CNN architecture called MyCNN that consists of two convolutional layers, two max pooling layers, and two fully connected layers. We then instantiated the model, defined a cross entropy loss criterion, and used the Adam optimizer to optimize the model parameters during training.

Use

Training a CNN in PyTorch is useful for a wide range of computer vision tasks, such as image classification, object detection, and segmentation. The process of training a CNN involves feeding input images through the model, computing the loss between the predicted and actual labels, and updating the model parameters to minimize the loss.

Important Points

  • Training a CNN in PyTorch involves defining the model architecture, loss criterion, and optimizer
  • PyTorch provides various built-in loss functions and optimizers for training neural networks
  • The goal of training a CNN is to minimize the loss between predicted and actual labels by updating the model parameters during training

Summary

In conclusion, training a Convolutional Neural Network in PyTorch involves defining the CNN architecture, loss criterion, and optimizer, and iterating over the training data to update the model parameters. PyTorch provides a variety of built-in loss functions and optimizers that can be used for training neural networks on a range of computer vision tasks.

CNN ImplementationValidation of CNN
Published on: