ImageDataGenerator用于语义分割

时间:2019-09-22 14:23:46

标签: python tensorflow keras semantic-segmentation

我正在尝试使用Keras进行语义分割,当尝试加载图像时,我使用flow_from_directory方法遇到了此错误。

Found 0 images belonging to 0 classes.
Found 0 images belonging to 0 classes.

这是我的代码。

from tensorflow.keras.applications.resnet50 import preprocess_input
from tensorflow.keras.preprocessing.image import ImageDataGenerator

data_generator = ImageDataGenerator()
train_generator = data_generator.flow_from_directory(
                                        directory="../input/Training_dataset/Images",
                                        target_size=(IMG_SIZE, IMG_SIZE),
                                        batch_size=16,
                                        class_mode=None,
                                        classes=None
                                        )

mask_generator = data_generator.flow_from_directory(
    directory="../input/Training_dataset/Masks/all",
    class_mode=None,
    classes=None,
    batch_size = 1,
    )

我已经阅读了此问题,但解决方案无效Keras for semantic segmentation, flow_from_directory() error

1 个答案:

答案 0 :(得分:1)

您需要将图像保留在一个子文件夹中,例如在图像和遮罩目录中创建一个名为“ img”的文件夹。

-- image
   -- img
      -- 1.jpg
      -- 2.jpg
-- mask
   -- img
      -- 1.png
      -- 2.png

Datagenerator应该类似于:-

seed = 909 # (IMPORTANT) to transform image and corresponding mask with same augmentation parameter.
image_datagen = ImageDataGenerator(width_shift_range=0.1,
                 height_shift_range=0.1,
                 preprocessing_function = image_preprocessing) # custom fuction for each image you can use resnet one too.
mask_datagen = ImageDataGenerator(width_shift_range=0.1,
                 height_shift_range=0.1,
                 preprocessing_function = mask_preprocessing)  # to make mask as feedable formate (256,256,1)

image_generator =image_datagen.flow_from_directory("dataset/image/",
                                                    class_mode=None, seed=seed)

mask_generator = mask_datagen.flow_from_directory("dataset/mask/",
                                                   class_mode=None, seed=seed)

train_generator = zip(image_generator, mask_generator)

如果您想为语义分割模型创建自己的自定义数据生成器,以更好地控制数据集,则可以检查我的kaggle内核,其中我曾使用camvid数据集训练UNET模型。

https://www.kaggle.com/mukulkr/camvid-segmentation-using-unet

如果您需要更好的扩充功能,可以查看此很棒的GitHub存储库- https://github.com/mdbloice/Augmentor