Keras 错误 - 预期 block5_pool 有 4 个维度，但得到形状为 (6, 1) 的数组？

Question

我正在尝试使用在 Keras 中预训练的 VGG16，但我不断收到此错误：

ValueError: Error when checking target: expected block5_pool to have 4 dimensions, but got array with shape (6, 1)

错误是什么意思？

Error when checking target: expected block5_pool to have 4 dimensions, but got array with shape (6, 1)

这是我的实际代码：

from keras import applications
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K


# dimensions of our images.
img_width, img_height = 224, 224

train_data_dir = 'database/train'
validation_data_dir = 'database/validation'
nb_train_samples = 2000
nb_validation_samples = 26
epochs = 50
batch_size = 20

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
print('VGG-16 Model loaded.')

top_model = Sequential()
top_model.add(ZeroPadding2D((1,1),input_shape=input_shape))
top_model.add(Conv2D(64, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(64, (3, 3), activation='relu'))
top_model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))

top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(128, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(128, (3, 3), activation='relu'))
top_model.add(MaxPooling2D((2,2), strides=(2,2)))

top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(256, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(256, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(256, (3, 3), activation='relu'))
top_model.add(MaxPooling2D((2,2), strides=(2,2)))

top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(MaxPooling2D((2,2), strides=(2,2)))

top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(ZeroPadding2D((1,1)))
top_model.add(Conv2D(512, (3, 3), activation='relu'))
top_model.add(MaxPooling2D((2,2), strides=(2,2)))
top_model.add(Flatten())

top_model.add(Dense(4096, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(12))
top_model.add(Activation('softmax'))

# note that it is necessary to start with a fully-trained
# classifier, including the top classifier,
# in order to successfully do fine-tuning
# top_model.load_weights('./vgg16_face_weights.h5')

# add the model on top of the convolutional base
model.add_update(top_model)

# set the first 25 layers (up to the last conv block)
# to non-trainable (weights will not be updated)
for layer in model.layers[:25]:
    layer.trainable = False

model.compile(loss='sparse_categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model.save_weights('first_try.h5')

航站楼运行:

VGG-16 Model loaded.
Found 46 images belonging to 12 classes.
Found 26 images belonging to 12 classes.
Epoch 1/50
Traceback (most recent call last):
  File "C:/Users/w024029h/PycharmProjects/keras_pretrained/pretrained.py", line 113, in <module>
    validation_steps=nb_validation_samples // batch_size)
  File "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 2230, in fit_generator
    class_weight=class_weight)
  File "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 1877, in train_on_batch
    class_weight=class_weight)
  File "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 1480, in _standardize_user_data
    exception_prefix='target')
  File "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 113, in _standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking target: expected block5_pool to have 4 dimensions, but got array with shape (6, 1)

Answer 1

我以前也遇到过同样的错误。我通过将数据生成器上的 class_mode 从 'binary' 更改为 None

来解决它

根据 keras 文档，将 class_mode 设置为 'binary' 将 return 一维数组。

通过更改 class_mode=None，不会 return 编辑任何标签，并且生成器只会生成批量图像数据。这就是您对模型的期望，并且与 fit_generator() 方法配合使用效果很好。但是，当使用 class_mode None 时，数据仍然需要驻留在 directory 的子目录中才能正常工作。

This page was useful to me

^看看flow_from_directory()

希望对您有所帮助！

Keras 错误 - 预期 block5_pool 有 4 个维度，但得到形状为 (6, 1) 的数组？

Keras Error - expected block5_pool to have 4 dimensions, but got array with shape (6, 1)?

python-3.x

keras

vgg-net