Classification of Fashion MNIST Images using different CNN architectures
Fashion MNIST is a dataset which consists of images of clothing. Each image is 28x28 grayscale image, with 10 different classes. The dataset contains 70000 images with 60000 for training and 10000 for testing. The Fashion-MNIST dataset is proposed as a more challenging replacement dataset for the MNIST dataset.
The mapping of all 0-9 integers to class labels is listed below :
- 0: T-shirt/top
- 1: Trouser
- 2: Pullover
- 3: Dress
- 4: Coat
- 5: Sandal
- 6: Shirt
- 7: Sneaker
- 8: Bag
- 9: Ankle boot
It is a more challenging classification problem than MNIST and top results are achieved by deep learning convolutional neural networks with a classification accuracy of about 90% to 95% on the hold out test dataset. In the code below an accuracy of around 92% has been achieved using many layers in Convolutional Neural Networks.