Keras VGG16微调

Question

有一个VGG16在keras blog上进行微调的例子，但是我无法复制它。

更准确地说，下面是用于初始化不带顶层的VGG16和冻结除顶层以外的所有块的代码：

WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file('vgg16_weights.h5', WEIGHTS_PATH_NO_TOP)

model = Sequential()
model.add(InputLayer(input_shape=(150, 150, 3)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))

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

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

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

model.add(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1'))
model.add(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2'))
model.add(Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2), name='block5_maxpool'))

model.load_weights(weights_path)

for layer in model.layers:
    layer.trainable = False

for layer in model.layers[-4:]:
    layer.trainable = True
    print("Layer '%s' is trainable" % layer.name)  

接下来，创建具有单个隐藏层的顶部模型：

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'))
top_model.load_weights('top_model.h5')

请注意，它以前接受过瓶颈特性方面的培训，如博客文章中所述。接下来，将此顶部模型添加到基本模型并编译：

model.add(top_model)
model.compile(loss='binary_crossentropy',
              optimizer=SGD(lr=1e-4, momentum=0.9),
              metrics=['accuracy'])

最后，根据猫/狗的数据：

batch_size = 16

train_datagen = ImageDataGenerator(rescale=1./255,
                                   shear_range=0.2,
                                   zoom_range=0.2,
                                   horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

train_gen = train_datagen.flow_from_directory(
    TRAIN_DIR,
    target_size=(150, 150),
    batch_size=batch_size,
    class_mode='binary')

valid_gen = test_datagen.flow_from_directory(
    VALID_DIR,
    target_size=(150, 150),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_gen,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=nb_epoch,
    validation_data=valid_gen,
    validation_steps=nb_valid_samples // batch_size)

但我在试着健身时犯了一个错误：

ValueError: Error when checking model target: expected block5_maxpool to have 4 > dimensions, but got array with shape (16, 1)

因此，基本模型中的最后一个池层似乎有问题。或者我在尝试将基本模型与顶部模型连接时做了一些错误的事情。

有没有类似的问题？或者也许有更好的方法来构建这样的“连接”模型？我正在使用keras==2.0.0和theano后端。

Note: I was using examples from gist and applications.VGG16 utility, but has issues trying to concatenate models, I am not too familiar with keras functional API. So this solution I provide here is the most "successful" one, i.e. it fails only on fitting stage.

---

更新1

好吧，这里有一个关于我要做什么的小解释。首先，我从VGG16生成瓶颈特性如下：

def save_bottleneck_features():
    datagen = ImageDataGenerator(rescale=1./255)
    model = applications.VGG16(include_top=False, weights='imagenet')

    generator = datagen.flow_from_directory(
        TRAIN_DIR,
        target_size=(150, 150),
        batch_size=batch_size,
        class_mode=None,
        shuffle=False)    
    print("Predicting train samples..")
    bottleneck_features_train = model.predict_generator(generator, nb_train_samples)
    np.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)

    generator = datagen.flow_from_directory(
        VALID_DIR,
        target_size=(150, 150),
        batch_size=batch_size,
        class_mode=None,
        shuffle=False)
    print("Predicting valid samples..")
    bottleneck_features_valid = model.predict_generator(generator, nb_valid_samples)
    np.save(open('bottleneck_features_valid.npy', 'w'), bottleneck_features_valid)

然后，我创建一个顶级模型，并对其进行以下功能培训：

def train_top_model():
    train_data = np.load(open('bottleneck_features_train.npy'))
    train_labels = np.array([0]*(nb_train_samples / 2) + 
                            [1]*(nb_train_samples / 2))
    valid_data = np.load(open('bottleneck_features_valid.npy'))
    valid_labels = np.array([0]*(nb_valid_samples / 2) +
                            [1]*(nb_valid_samples / 2))
    model = Sequential()
    model.add(Flatten(input_shape=train_data.shape[1:]))  
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])
    model.fit(train_data, train_labels,
              nb_epoch=nb_epoch,
              batch_size=batch_size,
              validation_data=(valid_data, valid_labels),
              verbose=1)
    model.save_weights('top_model.h5')   

因此，基本上，有两个训练模型，base_model具有ImageNet权重，top_model具有瓶颈特征生成的权重。我想知道如何连接它们？是可能的还是我做错了什么？因为正如我所见，@thomas pinetz的响应假设顶级模型不是单独训练的，而是直接附加到模型的。不确定我是否清楚，以下是博客中的一句话：

In order to perform fine-tuning, all layers should start with properly trained weights: for instance you should not slap a randomly initialized fully-connected network on top of a pre-trained convolutional base. This is because the large gradient updates triggered by the randomly initialized weights would wreck the learned weights in the convolutional base. In our case this is why we first train the top-level classifier, and only then start fine-tuning convolutional weights alongside it.

Answer 1

我想你可以通过这样做来连接两者：

#load vgg model
vgg_model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(150, 150, 3))
print('Model loaded.')

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


top_model.load_weights(top_model_weights_path)

# add the model on top of the convolutional base

model = Model(input= vgg_model.input, output= top_model(vgg_model.output))

此解决方案引用示例Fine-tuning the top layers of a a pre-trained network。完整的代码可以找到here。

Answer 2

我认为vgg网所描述的权重不符合您的模型，错误源于此。无论如何，有一种更好的方法可以使用（https://keras.io/applications/#vgg16）中描述的网络本身来实现这一点。

你可以使用：

base_model = keras.applications.vgg16.VGG16(include_top=False, weights='imagenet', input_tensor=None, input_shape=None)

实例化预先训练的vgg网络。然后，您可以冻结层并使用model类实例化您自己的模型，如下所示：

x = base_model.output
x = Flatten()(x)
x = Dense(your_classes, activation='softmax')(x) #minor edit
new_model = Model(input=base_model.input, output=x)

要组合底部和顶部网络，可以使用以下代码段。使用以下函数（输入层（https://keras.io/getting-started/functional-api-guide/）/加载模型（https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model）和keras的函数API）：

final_input = Input(shape=(3, 224, 224))
base_model = vgg...
top_model = load_model(weights_file)

x = base_model(final_input)
result = top_model(x)
final_model = Model(input=final_input, output=result)

Answer 3

好吧，我想Thomas和Gowtham发布了正确的（以及更简洁的答案），但是我想分享代码，我能够成功运行：

def train_finetuned_model(lr=1e-5, verbose=True):
    file_path = get_file('vgg16.h5', VGG16_WEIGHTS_PATH, cache_subdir='models')
    if verbose:
        print('Building VGG16 (no-top) model to generate bottleneck features.')

    vgg16_notop = build_vgg_16()
    vgg16_notop.load_weights(file_path)
    for _ in range(6):
        vgg16_notop.pop()
    vgg16_notop.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])    

    if verbose:
        print('Bottleneck features generation.')

    train_batches = get_batches('train', shuffle=False, class_mode=None, batch_size=BATCH_SIZE)
    train_labels = np.array([0]*1000 + [1]*1000)
    train_bottleneck = vgg16_notop.predict_generator(train_batches, steps=2000 // BATCH_SIZE)
    valid_batches = get_batches('valid', shuffle=False, class_mode=None, batch_size=BATCH_SIZE)
    valid_labels = np.array([0]*400 + [1]*400)
    valid_bottleneck = vgg16_notop.predict_generator(valid_batches, steps=800 // BATCH_SIZE)

    if verbose:
        print('Training top model on bottleneck features.')

    top_model = Sequential()
    top_model.add(Flatten(input_shape=train_bottleneck.shape[1:]))
    top_model.add(Dense(4096, activation='relu'))
    top_model.add(Dropout(0.5))
    top_model.add(Dense(4096, activation='relu'))
    top_model.add(Dropout(0.5))
    top_model.add(Dense(2, activation='softmax'))
    top_model.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])
    top_model.fit(train_bottleneck, to_categorical(train_labels),
                  batch_size=32, epochs=10,
                  validation_data=(valid_bottleneck, to_categorical(valid_labels)))

    if verbose:
        print('Concatenate new VGG16 (without top layer) with pretrained top model.')

    vgg16_fine = build_vgg_16()
    vgg16_fine.load_weights(file_path)
    for _ in range(6):
        vgg16_fine.pop()
    vgg16_fine.add(Flatten(name='top_flatten'))    
    vgg16_fine.add(Dense(4096, activation='relu'))
    vgg16_fine.add(Dropout(0.5))
    vgg16_fine.add(Dense(4096, activation='relu'))
    vgg16_fine.add(Dropout(0.5))
    vgg16_fine.add(Dense(2, activation='softmax'))
    vgg16_fine.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])

    if verbose:
        print('Loading pre-trained weights into concatenated model')

    for i, layer in enumerate(reversed(top_model.layers), 1):
        pretrained_weights = layer.get_weights()
        vgg16_fine.layers[-i].set_weights(pretrained_weights)

    for layer in vgg16_fine.layers[:26]:
        layer.trainable = False

    if verbose:
        print('Layers training status:')
        for layer in vgg16_fine.layers:
            print('[%6s] %s' % ('' if layer.trainable else 'FROZEN', layer.name))        

    vgg16_fine.compile(optimizer=RMSprop(lr=1e-6), loss='binary_crossentropy', metrics=['accuracy'])

    if verbose:
        print('Train concatenated model on dogs/cats dataset sample.')

    train_datagen = ImageDataGenerator(rescale=1./255,
                                       shear_range=0.2,
                                       zoom_range=0.2,
                                       horizontal_flip=True)
    test_datagen = ImageDataGenerator(rescale=1./255)
    train_batches = get_batches('train', gen=train_datagen, class_mode='categorical', batch_size=BATCH_SIZE)
    valid_batches = get_batches('valid', gen=test_datagen, class_mode='categorical', batch_size=BATCH_SIZE)
    vgg16_fine.fit_generator(train_batches, epochs=100,
                             steps_per_epoch=2000 // BATCH_SIZE,
                             validation_data=valid_batches,
                             validation_steps=800 // BATCH_SIZE)
    return vgg16_fine 

它有点太冗长了，所有的事情都是手工完成的（即，将权重从预先训练的层复制到连接的模型中），但它或多或少地起作用。

虽然我发布的这段代码有一个低精度的问题（大约70%），但那是另一回事。