Identifies breed of dog using CNN
We are provided with a training set and a test set of images of dogs. Each image has a filename that is its unique id. The dataset comprises 120 breeds of dogs. The goal is to create a classifier capable of determining a dog's breed from an image.
For the sake of a more efficient model, we reduced the total number of unique breeds from 120 to 60 and took only 5 unique breeds (classes) into consideration for training the CNN Model.
building the model using ResNet50V2.
Got a decent accuracy. We can improve the accuracy by increasing the number of epochs to 100 or 500. Also we can consider tuning the hyperparameters.