🌱 Introduction

πŸšͺ Beginning to solve problems of computer vision with Tensorflow and Keras

πŸ‘— What is MNIST?

The MNIST database: (Modified National Institute of Standards and Technology database)

  • πŸ”Ž Fashion-MNIST is consisting of a training set of 60,000 examples and a test set of 10,000 examples

  • 🎨 Types:

    • πŸ”’ MNIST: for handwritten digits

    • πŸ‘— Fashion-MNIST: for fashion

  • πŸ“ƒ Properties:

    • 🌚 Grayscale

    • 28x28 px

    • 10 different categories

    • ​Repo​

πŸ“š Important Terms

Term

Description

➰ Sequential

That defines a SEQUENCE of layers in the neural network

β›“ Flatten

Flatten just takes that square and turns it into a 1 dimensional set (used for input layer)

πŸ”· Dense

Adds a layer of neurons

πŸ’₯ Activation Function

A formula that introduces non-linear properties to our Network

✨ Relu

An activation function by the rule: If X>0 return X, else return 0

🎨 Softmax

An activation function that takes a set of values, and effectively picks the biggest one

The main purpose of activation function is to convert a input signal of a node in a NN to an output signal. That output signal now is used as a input in the next layer in the stack πŸ’₯

πŸ’« Notes on performance

  • Values in MNIST are between 0-255 but neural networks work better with normalized data, so we can divide every value by 255 so the values are between 0,1.

  • There are multiple criterias to stop training process, we can specify number of epochs or a threshold or both

    • Epochs: number of iterations

    • Threshold: a threshold for accuracy or loss after each iteration

    • Threshold with maximum number of epochs

We can check the accuracy at the end of each epoch by Callbacks πŸ’₯

πŸ‘©β€πŸ’» My Codes

🧐 References