错误 - 使用 Keras 的多分类神经网络

Question

我从我的 NN 代码中收到一个相当烦人的错误，我希望对 Keras 工作原理有更深入了解的人可以向我解释为什么我会收到该错误。我很感激任何帮助！ 错误：

AttributeError: 'DirectoryIterator' object has no attribute 'ndim'

错误来自：

    Traceback (most recent call last):
    File "C:\Users\Cameron\Desktop\AI\CubeFieldNN_Train -fix.py", line 80, in <module>
    validation_steps = (validation_samples / batch_size))

代码：

NN.fit(
train_set, train_labels,
batch_size = batch_size,
epochs = epochs,
validation_data = (validation_set, validation_labels),
validation_steps = (validation_samples / batch_size))

完整代码：https://pastebin.com/V1YwJW3X

完全错误：

    Traceback (most recent call last):
  File "C:\Users\Cameron\Desktop\AI\CubeFieldNN_Train -fix.py", line 80, in <module>
    validation_steps = (validation_samples / batch_size))
  File "C:\Python\lib\site-packages\keras\models.py", line 1002, in fit
    validation_steps=validation_steps)
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 1630, in fit
    batch_size=batch_size)
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 1476, in _standardize_user_data
    exception_prefix='input')
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 76, in _standardize_input_data
    data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
  File "C:\Python\lib\site-packages\keras\engine\training.py", line 76, in <listcomp>
    data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
AttributeError: 'DirectoryIterator' object has no attribute 'ndim'

Answer 1

从 fit_generator 从 previous question 转换到 fit 并不是真正必要的。 flow_from_directory 返回一个生成器类型对象，该对象返回数据和标签的元组。 validation_set 也是如此。另请注意，如果您指定validation_steps，您还必须指定steps_per_epoch。因此，您可以使用：

NN.fit_generator(train_set,
                 steps_per_epoch=steps_per_epoch,
                 epochs=epochs,
                 validation_data=validation_set,
                 validation_steps=validation_steps)

或者，您可以一次加载所有图像并将其与标签一起传递给NN.fit() 函数。