Loading the dataset

Use the methods defined in the Loading the dataset section when we created the Stage-I StackGAN. Load the high- and low-resolution datasets separately. Also, load the training and test datasets separately:

X_hr_train, y_hr_train, embeddings_train = load_dataset(filenames_file_path=filenames_file_path_train,
                                                        class_info_file_path=class_info_file_path_train,
                                                        cub_dataset_dir=cub_dataset_dir,
                                                        embeddings_file_path=embeddings_file_path_train,
                                                        image_size=(256, 256))

X_hr_test, y_hr_test, embeddings_test = load_dataset(filenames_file_path=filenames_file_path_test,
                                                     class_info_file_path=class_info_file_path_test,
                                                     cub_dataset_dir=cub_dataset_dir,
                                                     embeddings_file_path=embeddings_file_path_test,
                                                     image_size=(256, 256))

X_lr_train, y_lr_train, _ = load_dataset(filenames_file_path=filenames_file_path_train,
                                         class_info_file_path=class_info_file_path_train,
                                         cub_dataset_dir=cub_dataset_dir,
                                         embeddings_file_path=embeddings_file_path_train,
                                         image_size=(64, 64))

X_lr_test, y_lr_test, _ = load_dataset(filenames_file_path=filenames_file_path_test,
                                       class_info_file_path=class_info_file_path_test,
                                       cub_dataset_dir=cub_dataset_dir,
                                       embeddings_file_path=embeddings_file_path_test,
                                       image_size=(64, 64))