taarun-srinivas / fashion-mnist-classification-using-autoencoders

Scratch implementation of autoencoders to classify different classes in Fashion MNIST dataset

Fashion-MNIST-classification-using-autoencoders

Requirements

1. Python3
2. Pytorch
3. Matplotlib.pyplot

AutoEncoders

Autoencoders are a type of artificial neural network used for learning efficient data representations in an unsupervised manner. They aim to learn a compressed representation of the input data, often for the purpose of dimensionality reduction, noise reduction, or feature extraction. Autoencoders consist of an encoder and a decoder, which work in tandem to learn the representation.

Here's how autoencoders generally work: Encoder: The encoder takes an input and compresses it into a latent-space representation, also known as a bottleneck or encoding. This step involves reducing the dimensions of the input data. Decoder: The decoder takes the encoded representation and tries to reconstruct the original input from this representation. It aims to produce an output that is as close as possible to the original input.

About Dataset

Fashion MNIST is a popular dataset used for benchmarking machine learning algorithms, particularly in the field of computer vision. It is a dataset of Zalando's article images, consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. The classes are T-Shirt/Top, Trouser, Pullover, Dress, Coat, Sandal, Shirt, Sneaker, Bag, Ankle boot.

Visualization