Dog Breed Classifier

This repository contains the code and resources for the Dog Breed Classifier project. The project aims to classify dog breeds based on input images using deep learning techniques.

Project Structure

The repository includes the following files and directories:

• __pycache__: A directory containing cached Python files.

• pet_images: A directory containing images of pets for classification.

• uploaded_images: A directory containing uploaded images for classification.

• README.md: The README file providing an overview of the project.

• adjust_results4_isadog.py: A Python script to adjust the results for identifying dogs.

• adjust_results4_isadog_hints.py: Hints for adjusting the results for identifying dogs.

• alexnet_uploaded-images.txt: A text file containing the predictions from AlexNet model for uploaded images.

• calculates_results_stats.py: A Python script to calculate statistics for the model results.

• calculates_results_stats_hints.py: Hints for calculating statistics for the model results.

• check_images.py: A Python script to check the images for consistency and quality.

• check_images.txt: A text file containing the output of checking the images.

• classifier.py: The main Python script for classifying dog breeds.

• classify_images.py: A Python script to classify images using the trained models.

• classify_images_hints.py: Hints for classifying images using the trained models.

• dognames.txt: A text file containing a list of dog names.

• get_input_args.py: A Python script to get input arguments from the command line.

• get_input_args_hints.py: Hints for getting input arguments from the command line.

• get_pet_labels.py: A Python script to extract pet labels from file names.

• get_pet_labels_hints.py: Hints for extracting pet labels from file names.

• imagenet1000_clsid_to_human.txt: A text file mapping ImageNet class IDs to human-readable labels.

• print_functions_for_lab_checks.py: A Python script containing print functions for lab checks.

• print_results.py: A Python script to print the model results.

• print_results_hints.py: Hints for printing the model results.

• resnet_uploaded-images.txt: A text file containing the predictions from ResNet model for uploaded images.

• run_models_batch.sh: A shell script to run the models on a batch of images.

• run_models_batch_uploaded.sh: A shell script to run the models on uploaded images.

• test_classifier.py: A Python script to test the classifier.

• vgg_uploaded-images.txt: A text file containing the predictions from VGG model for uploaded images.

Usage

To use the Dog Breed Classifier, follow these steps:

1. Clone or download the repository to your local machine.

2. Ensure that you have Python and the necessary dependencies installed.

3. Place the images you want to classify in the pet_images directory or the uploaded_images directory, depending on the type of images.

4. Run the appropriate scripts to perform tasks such as adjusting results, calculating statistics, checking images, classifying images, or testing the classifier.

5. Review the generated output files and console logs to analyze the results of the classification.

6. Modify the code as needed or use it as a reference to build your own dog breed classifier.

License

This project does not have a specific license as the provided code snippets are part of a Udacity project. Please refer to the original source and Udacity's terms and conditions for any licensing requirements.

Acknowledgements

The Dog Breed Classifier project and the code snippets provided are part of the Udacity "AI Programming with Python" course. Special thanks to Udacity for providing the project materials and resources for learning about deep learning and image classification.