1. Project Motivation
2. File Descriptions
3. Required Libraries
4. Instructions
5. Results

Image Classifier Project is a requirement to complete the AI Programming with Python Nanodegree Program of udacity academy.

The project goal is to build a Python application that can train an image classifier on a dataset, then predicts new images using the trained model. For this purpose, I built and trained an image classifier to recognize different species of flowers. I used this dataset of 102 flower categories, you can see a few examples below.

The project is broken down into multiple steps:

• Load and preprocess the image dataset
• Train the image classifier on your dataset
• Use the trained classifier to predict image content

• Image Classifier Project.ipynb: a Jupyter notebook, contains the whole project code to build and train an image classifier.
• train.py: trains a new network on a dataset and saves the model as a checkpoint.
• predict.py: uses a trained network to predict the class for an input image.
• cat_to_name.json: a JSON object which gives you a dictionary mapping the integer encoded categories to the actual names of the flowers.

• PyTorch
• NumPy
• matplotlib

• Train a new network on a data set with train.py

  • Basic usage: python train.py data_directory
  • Prints out training loss, validation loss, and validation accuracy as the network trains
  • Options:
    • Set directory to save checkpoints: python train.py data_dir --save_dir save_directory
    • Choose architecture: python train.py data_dir --arch "vgg13"
    • Set hyperparameters: python train.py data_dir --learning_rate 0.01 --hidden_units 512 --epochs 20
    • Use GPU for training: python train.py data_dir --gpu

• Predict flower name from an image with predict.py along with the probability of that name. That is, you'll pass in a single image /path/to/image and return the flower name and class probability.

  • Basic usage: python predict.py /path/to/image checkpoint
  • Options:
    • Return top K most likely classes: python predict.py input checkpoint --top_k 3
    • Use a mapping of categories to real names: python predict.py input checkpoint --category_names cat_to_name.json
    • Use GPU for inference: : Use GPU for inference: python predict.py input checkpoint --gpu

• The testing accuracy of the trained network on the 10000 test images is 89%.
• For sanity checking, I tested the trained network on the english marigold flower, and returned the top 5 classes. As a result, it gave the correct class, the highest probability.