Created using Colab

[Shrutakeerti]

Description

In developing the fashion classification model using the Fashion MNIST dataset, a convolutional neural network (CNN) architecture was employed due to its proven efficacy in image classification tasks. The data preprocessing involved normalizing pixel values to a range between 0 and 1 and reshaping images to fit the network's input requirements. The CNN was designed with multiple convolutional and pooling layers to capture spatial hierarchies in the images, and ReLU activation functions were used to introduce non-linearity. Dropout layers were integrated to mitigate overfitting, and fully connected dense layers were utilized towards the network's end to make the final predictions. The model was trained using the Adam optimizer for its efficiency in handling sparse gradients, with categorical cross-entropy as the loss function appropriate for multi-class classification. Throughout training, careful attention was given to selecting the number of epochs and batch size to balance performance and training time. The model's performance was rigorously evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure it generalized well to unseen data.

Fixes #378

Type of change

• [x] Added a new machine learning frameworks, libraries or software.
• [x] Documentation update

Checklist:

• [x] My code follows the style guidelines of this project
• [x] I have performed a self-review of my own code
• [x] I have commented my code, particularly in hard-to-understand areas
• [x] I have made corresponding changes to the documentation
• [x] My changes generate no new warnings

[github-actions[bot]]

Thank you for submitting your pull request! 🙌 We'll review it as soon as possible. In the meantime, please ensure that your changes align with our CONTRIBUTING.md. If there are any specific instructions or feedback regarding your PR, we'll provide them here. Thanks again for your contribution! 😊