This is the second project for Udacity's Intro to Machine Learning with TensorFlow Nanodegree Program to learn about Deep Learning using TensorFlow. The notebook utilizes MobileNetV2 feature extractor as the base model to classify novel flower images.
This project requires Python 3.x and the following Python libraries installed:
You will also need to have software installed to run and execute an iPython Notebook
We recommend students install Anaconda, a pre-packaged Python distribution that contains all of the necessary libraries and software for this project.
Project_Image_Classifier_Project.ipynb
: This is the main notebook to create and train a TensorFlow Keras model to predict the type of a flower from its image.Project_Image_Classifier_Project.html
: HTML format of the notebook for viewing in browserpredict.py
: The command line application that implements the trained deep learning network to classify an input flower image.model1581751950.h5
: The final deep learning model that predicts the flower type from its image with above 90% accuracy.label_map.json
: The mapping of the key values to their corresponding flower types.workspace-utils.py
: The supporting methods to keep the notebook active during long deep learning training phase.
In a terminal or command window, navigate to the top-level project directory (that contains this README) and run one of the following commands:
ipython notebook Project_Image_Classifier_Project.ipynb
or
jupyter notebook Project_Image_Classifier_Project.ipynb
This will open the iPython Notebook software and project file in your browser.
Important Notice: The deep learning network for this project is very deep and dense. Thus, running this notebook might require GPU to be enabled.
The dataset used is Oxford 102 Category Flower Dataset.
This project is for Udacity's Nanodegree Program and all the copyrights belong to Udacity.