Dog Breed Identification Using Pre-Trained Models

Dog breed identification problem has many inter-class similarities and makes it difficult to classify or identify dogs which have similarities, we have about 130 different dog breeds and they are identified by convolutional neural network using transfer learning pre-trained models ResNet50 to obtain an accuracy of 82.7%, we use OpenCV implementation to detect human faces and to predict the nearest resemblance to a breed of dog, so if misclassified as human the predicted breed can be known. We use 30 epochs and a batch size of 64 to achieve this accuracy.