Skip to content

Cloth Classification (Feed forward neural net vs sequence model)

Notifications You must be signed in to change notification settings

arnab39/Cloth_Classification_DeepLearning

Repository files navigation

Cloth Classification using Deep Learning

This repository contains three different implementation of cloth classification.

Link to cloth classification data: https://drive.google.com/open?id=1EtWSWBtrIcIIx5rUTSRAIgJd6Vb8rvwW

About the dataset:
●train_images: 60000 examples of 28x28 grayscale image. The data is of size 60000 x 784. Each pixel has a single intensity value which is an integer between 0 and 255.
●train_labels: 60000 labels from 10 classes for the images in given in train_images. Class details are mentioned below.
●test_images: 10000 examples of 28x28 grayscale image. The data is of size 10000 x 784. Each pixel has a single intensity value which is an integer between 0 and 255.
●test_labels: 10000 labels from 10 classes for the images in given in test_images. Class details are mentioned below.

Enter each folder to run cloth classification using different techniques. The first folder has the Sequence model based classification while the next two folder has simple feed-forward neural network based classification using both tensorflow and only python(No tensorflow libraries allowed).

The folder also has two basic codes for Regression and kNN classifier using jupyter notebook.