图像看起来”；“错误”；从keras张量转换为numpy数组后

我正在将数据集从keras张量转换为numpy数组，以执行K倍交叉验证。我在k折叠中的准确度与之前运行模型相比真的很低。当我查看数据时，我注意到转换后的图像大多是黑色/白色/蓝色，而且很糟糕。是的，它是一只苍蝇

请参见下面的代码。是转换还是显示错误？

train_ds = tf.keras.utils.image_dataset_from_directory(
  directory ='/gdrive/My Drive/Flies_dt/224x224',
  validation_split=0.4,
  subset="training",
  seed=123,
  image_size=(224, 224),
  batch_size=32,
  shuffle=False)

val_ds = tf.keras.utils.image_dataset_from_directory(
  directory ='/gdrive/My Drive/Flies_dt/224x224',
  validation_split=0.4,
  subset="validation",
  seed=123,
  image_size=(224, 224),
  batch_size=32,
  shuffle=False)

train_images = np.concatenate(list(train_ds.map(lambda x, y:x)))
train_labels = np.concatenate(list(train_ds.map(lambda x, y:y)))

val_images = np.concatenate(list(val_ds.map(lambda x, y:x)))
val_labels = np.concatenate(list(val_ds.map(lambda x, y:y)))

inputs = np.concatenate((train_images, val_images), axis=0)
targets = np.concatenate((train_labels, val_labels), axis=0)

from matplotlib import pyplot as plt
plt.imshow(inputs[1])
plt.show()