我有以下声明
self.__Dir_Data = tf.keras.preprocessing.image_dataset_from_directory(self.__Dir_Path ,validation_split = 0.1 ,subset="training", seed = 1, labels='inferred', label_mode='int' ,batch_size=32 ,image_size=(124, 124))
我想从以下Dir数据中提取单独的验证数据
问候 DA
答案 0 :(得分:1)
在对image_dataset_from_directory的调用中,为train数据集设置subset ='training,并为验证集将其设置为'validation',如下所示
train_data=tf.keras.preprocessing.image_dataset_from_directory(self.__Dir_Path ,validation_split = 0.1 ,subset="training", seed = 1, labels='inferred', label_mode='int' ,batch_size=32 ,image_size=(124, 124))
validation_data=tf.keras.preprocessing.image_dataset_from_directory(self.__Dir_Path ,validation_split = 0.1 ,subset="validation", seed = 1, labels='inferred', label_mode='int' ,batch_size=32 ,image_size=(124, 124))