read_FlowersDataset.py 文件源码

def read_dataset(data_dir):
    pickle_filename = "flowers_data.pickle"
    pickle_filepath = os.path.join(data_dir, pickle_filename)
    if not os.path.exists(pickle_filepath):
        utils.maybe_download_and_extract(data_dir, DATA_URL, is_tarfile=True)
        flower_folder = os.path.splitext(DATA_URL.split("/")[-1])[0]
        result = create_image_lists(os.path.join(data_dir, flower_folder))
        print "Training set: %d" % len(result['train'])
        print "Test set: %d" % len(result['test'])
        print "Validation set: %d" % len(result['validation'])
        print "Pickling ..."
        with open(pickle_filepath, 'wb') as f:
            pickle.dump(result, f, pickle.HIGHEST_PROTOCOL)
    else:
        print "Found pickle file!"

    with open(pickle_filepath, 'rb') as f:
        result = pickle.load(f)
        training_images = result['train']
        testing_images = result['test']
        validation_images = result['validation']

        del result

    print ("Training: %d, Validation: %d, Test: %d" % (
        len(training_images), len(validation_images), len(testing_images)))
    return training_images, testing_images, validation_images