Dataset Overview

Dataset Name

Fashion MNIST

Dataset Description

Fashion MNIST is a dataset of clothing images, such as T‑shirts, trousers, dresses, etc. It contains 60,000 training images and 10,000 test images, each a 28 × 28 pixel grayscale image.

Dataset Structure

• Training set: 60,000 images
• Test set: 10,000 images

Data Preprocessing

• Image Normalization: Normalize pixel values to the [0, 1] range.
• Label Encoding: Apply one‑hot encoding to the labels.

Dataset Applications

The dataset is used for training and evaluating image classification models, enabling classification of clothing images.

Dataset Examples

• Image Size: 28 × 28 pixels
• Image Format: Grayscale image

Dataset Usage

• Model Training: Train models using TensorFlow.
• Model Evaluation: Evaluate model accuracy on the test set.
• Prediction: Predict on training set and external images.

Dataset Dependencies

• tensorflow
• numpy
• matplotlib
• pandas
• opencv-python