Project information

  • Category: Deep Learning
  • Project date: March, 2019
  • Project URL: Github
Photo by Oleg Gratilo on Unsplash

Image Classifier Model

In this project, I have implemented an image classification application using a deep learning model on a dataset of images. This project is completed under Udacity Data Scientist Nanodegree Requirement.

Project Requirements

Train an image classifier to recognize different species of flowers.

  • Load a pre-trained network (If you need a starting point, the VGG networks work great and are straightforward to use).
  • Define a new, untrained feed-forward network as a classifier, using ReLU activations and dropout.
  • Train the classifier layers using backpropagation using the pre-trained network to get the features.
  • Track the loss and accuracy on the validation set to determine the best hyperparameters.

Skills Required

Python
Pandas
Plotly
Matplotlib
numPy
seaborn
torchvision
torch

Techniques

Major Tasks

  • Loaded and preprocessed the image dataset.
  • Trained the image classifier on iris dataset.
  • Making predictions using trained classifier on new images running through python command line application.

Completed using Jupyter Notebook and python command line.