1 class_names = dataset.class_names 2 class_names "NameError:未定义名称'dataset‘“

Question

我有以下代码：

import tensorflow as tf
from  tensorflow.keras import models, layers
import matplotlib.pyplot as plt

IMAGE_SIZE = 256
BATCH_SIZE = 32

dataset = tf.keras.preprocessing.image_dataset_from_directory(
    "Plantvillage",
    shuffle= True,
    image_size = (IMAGE_SIZE,IMAGE_SIZE),
    batch_size = BATCH_SIZE
)

class_names = dataset.class_names
class_names

我搞错了：

1 class_names = dataset.class_names 2 class_names "NameError: name 'dataset' is not defined "

Answer 1

请提供image_dataset_from_directory内这个特定文件夹(Plantvillage)的完整路径，以访问数据集，根据其class_names，所有图像都驻留在不同的文件夹中。

例如，：假设我在"Data\dataset“文件夹中有一个猫和一个狗两个文件夹，每个文件夹都有20个猫图像和20个狗图像，那么您可以通过如下指定根路径来访问这两个文件夹：

dataset = tf.keras.preprocessing.image_dataset_from_directory(
    "D:\Data\Dataset",  # This will show the inside folder names along with each folder images count
    shuffle= True,
    image_size = (IMAGE_SIZE,IMAGE_SIZE),
    batch_size = BATCH_SIZE
)

class_names = dataset.class_names
class_names

输出：

        Found 40 files belonging to 2 classes.
Out[3]: ['Cat', 'Dog']