Keras 进行语义分割，flow_from_directory() 错误

Question

我试图使用我对 Keras 文档中示例代码的修改，该文档展示了在使用图像掩码代替标签（用于图像分割）的情况下如何设置 image_datagen.flow_from_directory() ，我们为每个像素预测 class）。

顺便说一下，我设置了featurewise_center = True，试图从每个图像的颜色通道中减去所有训练图像的每个颜色通道的平均值，这样在整个训练集中，每个颜色通道平均值将为 0。我希望这不是实现此目的的方法。

无论如何，这是我生成错误的代码：

image_datagen = ImageDataGenerator(featurewise_center = True)
mask_datagen = ImageDataGenerator()

image_generator = image_datagen.flow_from_directory(
    '/home/icg/Martin/train_data_graz/images_rect_r640x360',
    class_mode = None,
    batch_size = 1,
    seed = 123)

mask_generator = mask_datagen.flow_from_directory(
    '/home/icg/Martin/train_data_graz/labels_rect_r640x360',
    class_mode = None,
    batch_size = 1,
    seed = 123)

# combine generators into one which yields image and masks
train_generator = zip(image_generator, mask_generator)

model.fit_generator(
    train_generator,
    steps_per_epoch = 1000,
    epochs = 100)

这是错误消息：

Found 0 images belonging to 0 classes.
Found 0 images belonging to 0 classes.
Traceback (most recent call last):
  File "FCN_VGG16.py", line 178, in <module>
    train_generator = zip(image_generator, mask_generator)
  File "/home/icg/rafa/local/lib/python2.7/site-packages/keras/preprocessing/image.py", line 1026, in next
    index_array, current_index, current_batch_size = next(self.index_generator)
  File "/home/icg/rafa/local/lib/python2.7/site-packages/keras/preprocessing/image.py", line 720, in _flow_index
    current_index = (self.batch_index * batch_size) % n
ZeroDivisionError: integer division or modulo by zero

由于某种原因 n = 0。知道为什么会发生这种情况吗？

Answer 1

您需要将每个 class 的图像放入 子文件夹 到您的 flow_from_directory() 功能目录中。

你的情况：

/home/icg/Martin/train_data_graz/images_rect_r640x360/images_class01
/home/icg/Martin/train_data_graz/images_rect_r640x360/images_class02
…

编辑：

由于您已将 class_mode 设置为 None 并进行语义分割（参见评论和 post）：

/home/icg/Martin/train_data_graz/images_rect_r640x360/all_images

Keras 进行语义分割，flow_from_directory() 错误

Keras for semantic segmentation, flow_from_directory() error

runtime-error

keras-2