PyTorch torch.nn.Conv2d() Method

by

PyTorch torch.nn.Conv2d class is “used for applying a 2D convolution over an input tensor, typically used in image processing tasks within a neural network.”

Syntax

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, 
                padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros')

Parameters

  1. in_channels: Number of channels in the input tensor (e.g., 3 for an RGB image).
  2. out_channels: Number of channels in the output tensor (i.e., number of filters to use).
  3. kernel_size: Size of the filter to use. This can be an integer (for square filters) or a tuple (for rectangular filters).
  4. stride: The stride of the convolution operation. Can be a single integer or a tuple. Default is 1.
  5. padding: Zero-padding added to both sides of the input. Can be a single integer or a tuple. Default is 0.
  6. dilation: Spacing between kernel elements. Default is 1.
  7. groups: Controls the connections between inputs and outputs. Default is 1 (standard convolution). Use groups=in_channels for depthwise convolution.
  8. bias: If True, adds a learnable bias to the output. Default is True.
  9. padding_mode: Specifies the padding mode to use. Default is ‘zeros’.

Example 1: Basic Example

Here is a simple example where we define a 2D convolutional layer with a single input channel, a single output channel, and a kernel size of 3×3:

import torch
import torch.nn as nn

# Define the Conv2d layer
conv = nn.Conv2d(1, 1, 3)

input_tensor = torch.randn(1, 1, 5, 5)

# Perform the convolution
output_tensor = conv(input_tensor)

print(output_tensor)

Output

Basic Example

Example 2: Multiple channels

In this example, we have three input channels and 16 output channels, often seen in the first layer of a CNN dealing with RGB images:

import torch
import torch.nn as nn

# Define the Conv2d layer
conv = nn.Conv2d(3, 16, 3)

input_tensor = torch.randn(1, 3, 5, 5)

# Perform the convolution
output_tensor = conv(input_tensor)

print(output_tensor)

Output

Multiple channels

Example 3: Stride and Padding

Here, we set stride and padding:

import torch
import torch.nn as nn

conv = nn.Conv2d(1, 1, 3, stride=2, padding=1)

input_tensor = torch.randn(1, 1, 5, 5)

# Perform the convolution
output_tensor = conv(input_tensor)

print(output_tensor)

Output

tensor([[[[ 0.5023, 0.3969, 1.0621],
          [-0.2315, 0.3366, 0.1586],
          [ 0.3768, 0.4520, 0.3447]]]], grad_fn=<ConvolutionBackward0>)

That’s it!

Related posts

torch.clone()

torch.squeeze()

torch.sum()

torch.full()

Post Views: 2

Leave a Comment