找不到 Keras TensorFlow 图像数据

Question

我正在尝试训练我的模型来读取一些 X 射线图像，我正在使用 Jupyter Notebook，我导入了库，定义了图像属性，准备了数据集，创建了神经网络模型，定义了回调...并管理了数据，但现在我在尝试训练模型时遇到了这个错误。

train_datagen = ImageDataGenerator(rotation_range=15,
                                    rescale=1./255,
                                    shear_range=0.1,
                                    zoom_range=0.2,
                                    horizontal_flip=True,
                                    width_shift_range=0.1,
                                    height_shift_range=0.1
                                    )
    train_generator = train_datagen.flow_from_dataframe(train_df,
                                                     "C:/Users/lenovo/PneumoniaClassification/chest_xray/train",x_col='filename',y_col='category',
                                                     target_size=Image_Size,
                                                     class_mode='categorical',
                                                     batch_size=batch_size)
    validation_datagen = ImageDataGenerator(rescale=1./255)
    validation_generator = validation_datagen.flow_from_dataframe(
        validate_df, 
        "C:/Users/lenovo/PneumoniaClassification/chest_xray/train", 
        x_col='filename',
        y_col='category',
        target_size=Image_Size,
        class_mode='categorical',
        batch_size=batch_size
    )
    test_datagen = ImageDataGenerator(rotation_range=15,
                                    rescale=1./255,
                                    shear_range=0.1,
                                    zoom_range=0.2,
                                    horizontal_flip=True,
                                    width_shift_range=0.1,
                                    height_shift_range=0.1)
    test_generator = train_datagen.flow_from_dataframe(train_df,
                                                     "C:/Users/lenovo/PneumoniaClassification/chest_xray/test",x_col='filename',y_col='category',
                                                     target_size=Image_Size,
                                                     class_mode='categorical',
                                                     batch_size=batch_size)

这是错误代码

Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
C:\Users\lenovo\AppData\Roaming\Python\Python39\site-packages\keras_preprocessing\image\dataframe_iterator.py:279: UserWarning: Found 2 invalid image filename(s) in x_col="filename". These filename(s) will be ignored.
  warnings.warn(
C:\Users\lenovo\AppData\Roaming\Python\Python39\site-packages\keras_preprocessing\image\dataframe_iterator.py:279: UserWarning: Found 1 invalid image filename(s) in x_col="filename". These filename(s) will be ignored.
  warnings.warn(
C:\Users\lenovo\AppData\Roaming\Python\Python39\site-packages\keras_preprocessing\image\dataframe_iterator.py:279: UserWarning: Found 2 invalid image filename(s) in x_col="filename". These filename(s) will be ignored.
  warnings.warn(

路径如下：

Answer 1

train 文件夹中有两个文件夹 NORMAL 和 PNEUMONIA？如果是这样，那么您需要使用 flow_from_directory 而不是 flow_from_dataframe:

base_dir = "C:/Users/lenovo/PneumoniaClassification/chest_xray"
train_dir = os.path.join(base_dir, 'train')
test_dir = os.path.join(base_dir, 'test')
validation_dir = os.path.join(base_dir, 'val')


train_datagen = ImageDataGenerator(rotation_range=15,
                                    rescale=1./255,
                                    shear_range=0.1,
                                    zoom_range=0.2,
                                    horizontal_flip=True,
                                    width_shift_range=0.1,
                                    height_shift_range=0.1
                                    )
train_generator = train_datagen.flow_from_directory(
        train_dir,  # This is the source directory for training images
        target_size=Image_Size,  # All images will be resized 
        batch_size=BATCH_SIZE,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_datagen = ImageDataGenerator(rescale=1./255)

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=Image_Size,
        batch_size=BATCH_SIZE,
        class_mode='binary')

test_datagen = ImageDataGenerator(rotation_range=15,
                                    rescale=1./255,
                                    shear_range=0.1,
                                    zoom_range=0.2,
                                    horizontal_flip=True,
                                    width_shift_range=0.1,
                                    height_shift_range=0.1)

test_generator = test_datagen.flow_from_directory(
        test_dir,
        target_size=Image_Size,
        batch_size=BATCH_SIZE,
        class_mode='binary')

找不到 Keras TensorFlow 图像数据

Keras TensorFlow Image Data cannot be found

python

tkinter

keras

tensorflow