def load_knifey(): knifey.maybe_download_and_extract() dataset = knifey.load() x_train, y_train_cls, y_train = dataset.get_training_set() x_test, y_test_cls, y_test = dataset.get_test_set() cls_names = dataset.class_names y_train = y_train.astype(np.float32) y_test = y_test.astype(np.float32) y_train_cls = y_train_cls.astype(np.int32) y_test_cls = y_test_cls.astype(np.int32) data = (x_train, y_train_cls, y_train, x_test, y_test_cls, y_test, cls_names) return data
import prettytensor as pt from sklearn.decomposition import PCA from sklearn.manifold import TSNE from sklearn.metrics import confusion_matrix import knifey from knifey import num_classes knifey.maybe_download_and_extract() data_dir = knifey.data_dir # 载入数据集,程序会遍历子文件夹来获取所有*.jpg格式的图像, # 然后将文件名放入训练集和测试集的两个列表中。 # 实际此时并未载入图像,而是在计算好transfer-values之后再执行载入 dataset = knifey.load() # 自己的数据 # 创建一个dataset.py模块中的DataSet对象,最好使用load_cache()封装函数 # 它会自动将图像列表保存到缓存文件中,因此需要确保列表顺序和后面生成的 # transfer-values顺序一致 # This is the code you would run to load your own image-files. # It has been commented out so it won't run now. # from dataset import load_cached # dataset = load_cached(cache_path='my_dataset_cache.pkl', in_dir='my_images/') # num_classes = dataset.num_classes # 获取类别名 class_names = dataset.class_names