Skip to content

Built and trained my own image classifier from scratch using Pytorch. A collection of projects, mini-projects and exercises I have completed as part of my Udacity AI Programming Nanodegree Programme.

License

Notifications You must be signed in to change notification settings

Ali-Parandeh/Udacity_AI_Programming_Nanodegree

Repository files navigation

Udacity AI Programming Nanodegree

A collection of exercises and mini-projects I have completed as part of my Udacity AI Programming Nanodegree Programme.

The nanodegree included a series of projects, mini-projects and quizes which are included in this repo.

Projects

  • Develop a python programme to compare performance of three pre-trained classifiers in classifying dogs and their breeds.
  • Develop your own image classifier from scratch using pytorch to classify flowers by their types
  • Develop a command line application to allow others to use the flower classifier

Mini-Projects

  • Implementing OOP for Clothing
  • Implementing Gaussian Distributions with OOP
  • Implementing Inheritance OOP for Clothing
  • Implementing Inheritance for Probability Distributions
  • Undertaking Mean Normalization and Data Separation with Numpy
  • Developing Statistics From Stock Data with Pandas
  • Visualising Data with Bar Charts, Histograms, Scatter plot, Violin and Box Plot, Scales and Transformations, Categorical Plot with Matplotlib
  • Vectors Lab, Linear Combination Lab, Linear Mapping Lab
  • Implementing Gradient Descent
  • Predicting Student Admissions with Neural Networks
  • Deep Learning with Pytorch
    • Part 1: Introduction to PyTorch and using tensors
    • Part 2: Building a fully-connected neural networks with PyTorch
    • Part 3: Training a fully-connected network with backpropagation on MNIST (Handwritten Digits)
    • Part 4: Training neural network on Fashion-MNIST
    • Part 5: Using a trained network for making predictions and validating networks, Implementing Dropout to avoid overfitting
    • Part 6: Saving and loading trained models
    • Part 7: Loading image data with torchvision, also data augmentation
    • Part 8: Using transfer learning to train a state-of-the-art image classifier for dogs and cats

Exercises:

  • Python
    • Data Types and Variables: Arithmetic Operators, Variables and Assignment Operators, Integers and Floats, Booleans - Comparison Operators and Logical Operators, Strings, Type and Type Conversion, String Methods
    • Data Structures: Lists and Membership Operators, List Methods, Tuples, Sets, Dictionaries and Identity Operators, Compound Data Structures
    • Control Flow: Conditional Statements, Boolean Expressions for Conditions, For Loops, Iterating Through Dictionaries, While Loops, Break and Continue, Zip and Enumerate, List Comprehensions
    • Functions: Defining Functions, Variable Scope, Function Documentation, Lambda Expressions, Iterators and Generators
    • Scripting: Scripting with Raw Input, Errors and Exceptions, Handling Input Errors, Reading and Writing Files, The Standard Library
    • OOP: OOP Syntax, Magic Methods, Inheritance
  • Numpy: Creating ndarrays, Manipulating ndarrays, Broadcasting
  • Pandas: Manipulate a Series, Manipulate a DataFrame
  • Linear Algebra: Vectors, Linear Combination and Transformation

About

Built and trained my own image classifier from scratch using Pytorch. A collection of projects, mini-projects and exercises I have completed as part of my Udacity AI Programming Nanodegree Programme.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published