The objective of this project is to improve programming skills using Python by applying an already developed image classifier to identify dog breeds. The classifier will be provided and the focus of the project is on using Python to utilize the classifier, rather than on creating the classifier itself.
The project is being undertaken as part of a citywide dog show, where participants must submit images of their dogs along with biographical information. The goal is to use the classifier to ensure that only actual dogs are registered for the show.
The instructions for this project are as follows:
- Correctly identify which pet images are dogs and which are not.
- Correctly classify the breed of dog for images that are of dogs.
- Determine which CNN model architecture (ResNet, AlexNet, or VGG) is the most effective in achieving the first two objectives.
- Consider the time and resources required to achieve the first two objectives, and determine whether an alternative solution would be sufficient given the time constraints.
The project involves using a CNN (Convolutional Neural Network) to classify pet images as either being of a dog or not, and to correctly identify the breed of dog for images that are of dogs. The goal is to determine which of the three specified CNN model architectures is the most effective in achieving these objectives. The time and resources required to achieve these objectives will also be considered, with the possibility of finding an alternative solution if necessary.