[Keras] Keras面向小数据集的图像分类(retrain

这篇文章主要参考：

• Building powerful image classification models using very little data

其中文翻译有：

• keras面向小数据集的图像分类（VGG-16基础上fine-tune）实现（附代码）

相关的博客有：

• keras系列︱图像多分类训练与利用bottleneck features进行微调（三）
• keras系列︱迁移学习：利用InceptionV3进行fine-tuning及预测、完美案例（五）

---

说重点，在Keras中直接调用VGG / Inception_v3模型的时候出现了一点点问题，然后我使用 keras面向小数据集的图像分类（VGG-16基础上fine-tune）实现（附代码）中的源码Fine-tuning跑了一遍仍然有问题：

ValueError: The shape of the input to "Flatten" is not fully defined (got (None, None, 512). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model

主要出在 Flatten层，没有指定输入。
源码很短，如下：

"""
This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats
- put the cat pictures index 1000-1400 in data/validation/cats
- put the dogs pictures index 12500-13499 in data/train/dogs
- put the dog pictures index 13500-13900 in data/validation/dogs
So that we have 1000 training examples for each class, and 400 validation examples for each class.
In summary, this is our directory structure:
data/
    train/
        dogs/
            dog001.jpg
            dog002.jpg
            ...
        cats/
            cat001.jpg
            cat002.jpg
            ...
    validation/
        dogs/
            dog001.jpg
            dog002.jpg
            ...
        cats/
            cat001.jpg
            cat002.jpg
            ...
"""

from keras import applications
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense

# path to the model weights files.
weights_path = '../keras/examples/vgg16_weights.h5'
top_model_weights_path = 'fc_model.h5'
# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = 'cats_and_dogs_small/train'
validation_data_dir = 'cats_and_dogs_small/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16

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

# build a classifier model to put on top of the convolutional model
top_model = Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(1, activation='sigmoid'))

# 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(top_model_weights_path)

# add the model on top of the convolutional base
model.add(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

# compile the model with a SGD/momentum optimizer
# and a very slow learning rate.
model.compile(loss='binary_crossentropy',
              optimizer=optimizers.SGD(lr=1e-4, momentum=0.9),
              metrics=['accuracy'])

# prepare data augmentation configuration
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1. / 255)

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

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

# fine-tune the model
model.fit_generator(
    train_generator,
    samples_per_epoch=nb_train_samples,
    epochs=epochs,
    validation_data=validation_generator,
    nb_val_samples=nb_validation_samples)

但是，代码中已经明确指定了Flatten层的输入大小：

top_model.add(Flatten(input_shape=model.output_shape[1:]))

这个问题一直困扰了我很久，keras系列︱图像多分类训练与利用bottleneck features进行微调（三）这位同学也是卡在这了，没能解决。不过我半个多月后又碰到了这个问题，发现没法绕开，最终还是找到了解决方法。实际上不止我一个人遇到了这个问题，很多人都遇到了，只是解决方法很难在搜索引擎上检索到：

解决方法其实已经在图中体现出来了，VGG模型在调用时选择了“不含顶层网络”的情况下，需要指定输入。VGG16的输入图像尺寸为(224,224)，因此，将源代码中的：

model = applications.VGG16(weights='imagenet', include_top=False)

修改为如下即可：

model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(224,224,3))

需要注意的是，此时使用TensorFlow作为后端，因此图像数据格式为“channel_last”，如果使用theano则为(3,224,224)，如果使用Inception_v3网络，则需要修改为：input_shape=(299,299,3)。
修改完后再次运行程序，可能会有新错误：

model.add(top_model)
AttributeError: 'Model' object has no attribute 'add'

错误的原因是因为'Model'不含有'add'属性，没关系，我们可以使用函数式模型来解决无法'add'的问题，可以参考下图：

将源码中的：

top_model = Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(1, activation='sigmoid'))

# 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(top_model_weights_path)

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

修改为：

# 新建一个分类模型置于模型顶层,并初始化
x = model.output
x = Flatten()(x)
x = Dense(256, 
          kernel_initializer='RandomUniform',
          activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(Nb_classes, 
                    kernel_initializer='RandomUniform',
                    activation='softmax')(x)

# 给经典模型组合新的顶层网络
new_model = Model(model.input, x)

因为我没有之前Building powerful image classification models using very little data中训练得到的Top layer的参数，因此我跳过了top_model.load_weights(top_model_weights_path)直接选择了'RandomUniform'初始化。除此之外，都大同小异，无需修改。