Classifies pet images using a pretrained CNN model, compares these classifications to the true identity of the pets in the images, and summarizes how well the CNN performed on the image classification task. Note that the true identity of the pet (or object) in the image is indicated by the filename of the image. Therefore, your program must first extract the pet image label from the filename before classifying the images using the pretrained CNN model. With this program we will be comparing the performance of 3 different CNN model architectures to determine which provides the 'best' classification.
python check_images.py --dir <directory with images> --arch <model> --dogfile <file that contains dognames>python check_images.py --dir pet_images/ --arch vgg --dogfile dognames.txt