By popular demand, the Valentine's Day Offer has been extended to the weekend Flat 25% off on all courses. Use coupon code VDAY25 During checkout

 Enroll Now

Project - Classify Clothes

1 / 1

Project - Classify clothes using TensorFlow

About the Dataset

Fashion-MNIST 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. Zalando intends Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits. Zalando seeks to replace the original MNIST dataset

  • Training set - 60,000 examples
  • Test set - 10,000 examples
  • Each example is a 28x28 grayscale image
  • 10 classes

Dataset Path

On CloudxLab the data is available in the directory '/cxldata/datasets/project/fashion-mnist'

How to load the dataset

You can load the dataset as -
from tensorflow.examples.tutorials.mnist import input_data
fashion_mnist = input_data.read_data_sets("/cxldata/datasets/project/fashion-mnist")

Content of Dataset

Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. - Each row is a separate image - Column 1 is the class label. - Remaining columns are pixel numbers (784 total) - Each value is the darkness of the pixel (1 to 255)


Each training and test example is assigned to one of the following labels:

  • 0 - T-shirt/top

  • 1 - Trouser

  • 2 - Pullover

  • 3 - Dress

  • 4 - Coat

  • 5 - Sandal

  • 6 - Shirt

  • 7 - Sneaker

  • 8 - Bag

  • 9 - Ankle boot

Train a CNN model on this dataset. You are expected to achieve an accuracy of more than 90% in this project

After you are done, save your notebook as classify_clothes.ipynb in your home folder on CloudxLab.