Classifying clothing images with CNNs

As mentioned, the CNN model has two main components: the feature extractor composed of a set of convolutional and pooling layers, and the classifier backend, similar to a regular neural network.

Let’s start this project by architecting the CNN model.

Architecting the CNN model

We import the necessary module and initialize a Sequential-based model:

>>> import torch.nn as nn
>>> model = nn.Sequential()

For the convolutional extractor, we are going to use three convolutional layers. We start with the first convolutional layer with 32 small-sized 3 * 3 filters. This is implemented with the following code:

>>> model.add_module('conv1',
                     nn.Conv2d(in_channels=1,
                               out_channels=32,
                               kernel_size=3)
                    )
>>> model.add_module('relu1', nn.ReLU())

Note that we use ReLU...