Question

您好，我正在尝试在Keras上制作经过预训练的VGG16 但这总是给我错误：

ValueError：检查目标：预期的activation_1时出错形状（2622，），但数组的形状为（1，）

我正在尝试根据以下海报创建模型：Link

我还从here那里接受了预先训练的体重。可以在here

上读取此权重

这是我的代码：

from keras import applications
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential, Model
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense, ZeroPadding2D
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 = 800
epochs = 50
batch_size = 16

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

# build the VGG16 network
model = applications.VGG16(weights='imagenet', include_top=False)
print('VGG Pretrained Model loaded.')

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

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

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

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

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

model.add(Conv2D(4096, (7, 7), activation='relu'))
model.add(Dropout(0.5))
model.add(Conv2D(4096, (1, 1), activation='relu'))
model.add(Dropout(0.5))
model.add(Conv2D(2622, (1, 1)))
model.add(Flatten())
model.add(Activation('softmax'))

# model.load_weights('./vgg16_face_weights.h5')
#
# vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)

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

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 224,
    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. / 224)

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')

Answer 1

您可能在'database/train'和'database/validation'中只有一个文件夹。

请确保两个文件夹中都有2622个文件夹，以便keras可以正确生成标签。

下面是一个示例，显示标签的形状应为（batch_size，2622）。

# the above remains the same
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

import numpy as np

classes = 2622
batch_size = 4
y = np.zeros((batch_size, classes))
for i in range(batch_size):
    y[i, np.random.choice(classes)] = 1

model.fit(x=np.random.random((batch_size,)+input_shape), y=y, batch_size=batch_size)

model.save_weights('first_try.h5')

编辑：

要将最后一个Conv2D层从2622个滤镜更改为12个滤镜，同时保持已加载的权重，这是一种解决方法：

#define model and load_weights
#......

#build a new model based on the last model
conv = Conv2D(12, (1, 1))(model.layers[-4].output)
flatten = Flatten()(conv)
softmax = Activation('softmax')(flatten)
final_model = Model(inputs=model.input, outputs=softmax)

参考：Cannot add layers to saved Keras Model. 'Model' object has no attribute 'add'

Keras错误-预期activation_1的形状为（2622，），但数组的形状为（1，）

1 个答案: