Chris Pollett > Students > More

    Print View

    [Bio]

    [Blog]

    [CS 297 Proposal]

    [Del 1 - Write LaTex for Famous Mathematical Equations]

    [Del 2 - Exploring TensorFlow with MNIST Dataset]

    [Del 3 - Exploring Data Generation Approaches]

    [Del 4 - Decide the Neural Network Architecture]

    [CS 297 Report-PDF]

    [CS 298 Proposal]

    [CS 298 Report-PDF]

    [CS 298 Slides-PDF]

Exploring TensorFlow with MNIST Dataset

This deliverable involves exploring TensorFlow with MNIST dataset.

MNIST dataset is hosted on Yaan Lecun's website.

This dataset contains 70000 images of handwritten digits.

These images are divided into three parts as follow:

  1. 55000 data points of training data (mnist.train)
  2. 10000 points of test data (mnist.test)
  3. 5000 points of validation data (mnist.validation)

Each MNIST data point has 2 parts:

  1. Image of a handwritten digit (mnist.train.images)
  2. Corresponding label (mnist.train.label)
There were two tutorials which I closely followed while doing this exercise. Both the tutorials are from the official Tensorflow website.

My code and presentation: