ND230 Introduction to Machine Learning with TensorFlow Nanodegree Program

Projects and exercises for the Udacity Intro to Machine Learning with TensorFlow course.

Getting Started

The major problems I've solved during this nanodegree in the format of Jupyter notebooks for Supervised Learning project and Neural Networks exercises and project can be both viewed and re-run through the following links on Google Colaboratory and Kaggle platforms. The notebook for Unsupervised Learning project can only be viewed statically—for it's been supposed not to include the licensed datasets.

Supervised Learning

👉 Project: Finding Donors for CharityML

Introduction to Neural Networks with TensorFlow

#	Lesson	Link
1	Introduction to TensorFlow and using tensors
2	Building fully-connected neural networks with TensorFlow
3	How to train a fully-connected network with backpropagation on MNIST
4	Exercise–train a neural network on Fashion-MNIST
5	Using a trained network for making predictions and validating networks
6	How to save and load trained models
7	Load image data with ImageDataGenerator, and also data augmentation
8	Use transfer learning to train a state-of-the-art image classifier for dogs and cats

👉 Project: Create Your Own Image Classifier—TensorFlow

👨🏻‍💻👩🏻‍💻 The resulted app is named as flower_recognizer. To run it locally on your computer, download the built binaries for your OS from the release section:

Unsupervised Learning

👉 Project: Creating Customer Segments with Arvato

Installation

To run the notebooks and scripts in this repo locally on a computer with the exact dependencies, just run the following commands in a terminal, and open the link it offers at the end for a jupyter notebook:

python3 -m pip install jupyter-repo2docker
repo2docker https://github.com/shahrokh-bahtooei/intro-to-ml-tensorflow.git

Prerequisites:

Alternatively, this repo could be run over a conda environment:

git clone https://github.com/shahrokh-bahtooei/intro-to-ml-tensorflow.git
cd intro-to-ml-tensorflow
conda env create --prefix ./env -f environment_minimal.yml
conda activate env/
jupyter notebook

Prerequisites:

/

---

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.