[转移学习TypeError：'模块'对象不可调用

Question

我的机器学习项目遇到问题。我制作了一个CNN模型，我想在VGG16 VGG19 restnet模型和其他模型中对其进行测试，这是我认为将使其起作用的代码，我可以将vgg16更改为其他模型。但是，我不断收到此错误：

C：\ Users \ Acer \ Anaconda3 \ envs \ condas \ pythonw.exe C：/Users/Acer/PycharmProjects/condas/rawr.py使用TensorFlow后端追溯（最近一次通话）：在第9行的文件“ C：/Users/Acer/PycharmProjects/condas/rawr.py”my_new_model.add（vgg16.VGG16（include_top = False，pooling ='avg'，weights = resnet_weights_path））VGG16中的第97行的文件“ C：\ Users \ Acer \ Anaconda3 \ envs \ condas \ lib \ site-packages \ keras_applications \ vgg16.py”data_format = backend.image_data_format（），AttributeError：“ NoneType”对象没有属性“ image_data_format”

以退出代码1完成的过程

from keras.applications.vgg16 import vgg16
from keras.models import Sequential
from keras.layers import Dense, Flatten, GlobalAveragePooling2D

num_classes = 2
resnet_weights_path = 'C:/Users/Acer/imagerec/EDA'

my_new_model = Sequential()
my_new_model.add(vgg16.VGG16(include_top=False, pooling='avg', weights=resnet_weights_path))
my_new_model.add(Dense(num_classes, activation='softmax'))


my_new_model.layers[0].trainable = False

my_new_model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])

from keras.applications.vgg16 import preprocess_input
from keras.preprocessing.image import ImageDataGenerator

image_size = 224
data_generator = ImageDataGenerator(preprocessing_function=preprocess_input)


train_generator = data_generator.flow_from_directory(
        'C:/Users/Acer/imagerec/EDA',
        target_size=(image_size, image_size),
        batch_size=20,
        class_mode='categorical')

validation_generator = data_generator.flow_from_directory(
        'C:/Users/Acer/imagerec/EDA',
        target_size=(image_size, image_size),
        class_mode='categorical')

my_new_model.fit_generator(
        train_generator,
        steps_per_epoch=3,
        validation_data=validation_generator,
        validation_steps=1)

Answer 1

您需要呼叫vgg16.VGG16而不是vgg16