Application应用

Kera的应用模块Application提供了带有预训练权重的Keras模型，这些模型可以用来进行预测、特征提取和finetune

模型的预训练权重将下载到~/.keras/models/并在载入模型时自动载入

可用的模型

应用于图像分类的模型,权重训练自ImageNet：

Xception
VGG16
VGG19
ResNet50
InceptionV3

所有的这些模型(除了Xception)都兼容Theano和Tensorflow，并会自动基于~/.keras/keras.json的Keras的图像维度进行自动设置。例如，如果你设置image_dim_ordering=tf，则加载的模型将按照TensorFlow的维度顺序来构造，即“Width-Height-Depth”的顺序

应用于音乐自动标签(以Mel-spectrograms为输入)

MusicTaggerCRNN

图片分类模型的示例

利用ResNet50网络进行ImageNet分类

from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np

model = ResNet50(weights='imagenet')

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
# decode the results into a list of tuples (class, description, probability)
# (one such list for each sample in the batch)
print('Predicted:', decode_predictions(preds, top=3)[0])
# Predicted: [(u'n02504013', u'Indian_elephant', 0.82658225), (u'n01871265', u'tusker', 0.1122357), (u'n02504458', u'African_elephant', 0.061040461)]

利用VGG16提取特征

from keras.applications.vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np

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

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

features = model.predict(x)

从VGG19的任意中间层中抽取特征

from keras.applications.vgg19 import VGG19
from keras.preprocessing import image
from keras.applications.vgg19 import preprocess_input
from keras.models import Model
import numpy as np

base_model = VGG19(weights='imagenet')
model = Model(input=base_model.input, output=base_model.get_layer('block4_pool').output)

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

block4_pool_features = model.predict(x)

利用新数据集finetune InceptionV3

from keras.applications.inception_v3 import InceptionV3
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K

# create the base pre-trained model
base_model = InceptionV3(weights='imagenet', include_top=False)

# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(200, activation='softmax')(x)

# this is the model we will train
model = Model(input=base_model.input, output=predictions)

# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
    layer.trainable = False

# compile the model (should be done *after* setting layers to non-trainable)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')

# train the model on the new data for a few epochs
model.fit_generator(...)

# at this point, the top layers are well trained and we can start fine-tuning
# convolutional layers from inception V3. We will freeze the bottom N layers
# and train the remaining top layers.

# let's visualize layer names and layer indices to see how many layers
# we should freeze:
for i, layer in enumerate(base_model.layers):
   print(i, layer.name)

# we chose to train the top 2 inception blocks, i.e. we will freeze
# the first 172 layers and unfreeze the rest:
for layer in model.layers[:172]:
   layer.trainable = False
for layer in model.layers[172:]:
   layer.trainable = True

# we need to recompile the model for these modifications to take effect
# we use SGD with a low learning rate
from keras.optimizers import SGD
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy')

# we train our model again (this time fine-tuning the top 2 inception blocks
# alongside the top Dense layers
model.fit_generator(...)

在定制的输入tensor上构建InceptionV3

from keras.applications.inception_v3 import InceptionV3
from keras.layers import Input

# this could also be the output a different Keras model or layer
input_tensor = Input(shape=(224, 224, 3))  # this assumes K.image_dim_ordering() == 'tf'

model = InceptionV3(input_tensor=input_tensor, weights='imagenet', include_top=True)

模型文档

## Xception模型 ```python keras.applications.xception.Xception(include_top=True, weights='imagenet', input_tensor=None，input_shape=None) ```

Xception V1 模型, 权重由ImageNet训练而言

在ImageNet上,该模型取得了验证集top1 0.790和top5 0.945的正确率

注意,该模型目前仅能以TensorFlow为后端使用,由于它依赖于"SeparableConvolution"层,目前该模型只支持tf的维度顺序(width, height, channels)

默认输入图片大小为299x299

参数

include_top：是否保留顶层的3个全连接网络
weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
input_tensor：可填入Keras tensor作为模型的图像输出tensor
input_shape: 可选参数，仅当include_top=False时才应指定该参数。input_shape须为长3的tuple，图片的宽和高不得小于71.

返回值

Keras 模型对象

参考文献

Xception: Deep Learning with Depthwise Separable Convolutions

License

预训练权重由我们自己训练而来，基于MIT license发布

## VGG16模型 ```python keras.applications.vgg16.VGG16(include_top=True, weights='imagenet', input_tensor=None， input_shape=None) ```

VGG16模型,权重由ImageNet训练而来

该模型再Theano和TensorFlow后端均可使用,并接受th和tf两种输入维度顺序

模型的默认输入尺寸时224x224

参数

include_top：是否保留顶层的3个全连接网络
weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
input_tensor：可填入Keras tensor作为模型的图像输出tensor
input_shape: 可选参数，仅当include_top=False时才应指定该参数。input_shape须为长3的tuple，维度顺序依赖于image_dim_ordering，图片的宽和高不得小于48.

返回值

Keras 模型对象

参考文献

Very Deep Convolutional Networks for Large-Scale Image Recognition：如果在研究中使用了VGG，请引用该文

License

预训练权重由牛津VGG组发布的预训练权重移植而来，基于Creative Commons Attribution License

## VGG19模型 ```python keras.applications.vgg19.VGG19(include_top=True, weights='imagenet', input_tensor=None， input_shape=None) ``` VGG19模型,权重由ImageNet训练而来

该模型再Theano和TensorFlow后端均可使用,并接受th和tf两种输入维度顺序

模型的默认输入尺寸时224x224

参数

include_top：是否保留顶层的3个全连接网络
weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
input_tensor：可填入Keras tensor作为模型的图像输出tensor
input_shape: 可选参数，仅当include_top=False时才应指定该参数。input_shape须为长3的tuple，维度顺序依赖于image_dim_ordering，图片的宽和高不得小于48.

返回值

Keras 模型对象

参考文献

Very Deep Convolutional Networks for Large-Scale Image Recognition：如果在研究中使用了VGG，请引用该文

License

预训练权重由牛津VGG组发布的预训练权重移植而来，基于Creative Commons Attribution License

## ResNet50模型 ```python keras.applications.resnet50.ResNet50(include_top=True, weights='imagenet', input_tensor=None, input_shape=None) ```

50层残差网络模型,权重训练自ImageNet

该模型再Theano和TensorFlow后端均可使用,并接受th和tf两种输入维度顺序

模型的默认输入尺寸时224x224

参数

include_top：是否保留顶层的全连接网络
weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
input_tensor：可填入Keras tensor作为模型的图像输出tensor
input_shape: 可选参数，仅当include_top=False时才应指定该参数。input_shape须为长3的tuple，维度顺序依赖于image_dim_ordering，图片的宽和高不得小于197.

返回值

Keras 模型对象

参考文献

Deep Residual Learning for Image Recognition：如果在研究中使用了ResNet50，请引用该文

License

预训练权重由Kaiming He发布的预训练权重移植而来，基于MIT License

## InceptionV3模型 ```python keras.applications.inception_v3.InceptionV3(include_top=True, weights='imagenet', input_tensor=None，input_shape=None) ``` InceptionV3网络,权重训练自ImageNet

该模型再Theano和TensorFlow后端均可使用,并接受th和tf两种输入维度顺序

模型的默认输入尺寸时299x299

参数

include_top：是否保留顶层的全连接网络
weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
input_tensor：可填入Keras tensor作为模型的图像输出tensor
input_shape: 可选参数，仅当include_top=False时才应指定该参数。input_shape须为长3的tuple，其维度顺序依赖于所使用的image_dim_ordering，图片的宽和高不得小于139.

返回值

Keras 模型对象

参考文献

Rethinking the Inception Architecture for Computer Vision：如果在研究中使用了InceptionV3，请引用该文

License

预训练权重由我们自己训练而来，基于MIT License

## MusicTaggerCRNN模型 ```python keras.applications.music_tagger_crnn.MusicTaggerCRNN(weights='msd', input_tensor=None, include_top=True) ``` 该模型时一个卷积循环模型,以向量化的MelSpectrogram音乐数据为输入,能够输出音乐的风格. 你可以用`keras.applications.music_tagger_crnn.preprocess_input`来将一个音乐文件向量化为spectrogram.注意,使用该功能需要安装[Librosa](http://librosa.github.io/librosa/),请参考上面的使用范例. ### 参数 * include_top：是否保留顶层的全连接网络 * weights：None代表随机初始化，即不加载预训练权重。'imagenet'代表加载预训练权重 * input_tensor：可填入Keras tensor作为模型的图像输出tensor

返回值

Keras 模型对象

参考文献

Rethinking the Inception Architecture for Computer Vision：如果在研究中使用了InceptionV3，请引用该文

License

预训练权重由我们自己训练而来，基于MIT License

引用

https://github.com/MoyanZitto/keras-cn/blob/master/docs/other/application.md~

Keras迁移学习提取特征

Application应用

可用的模型

图片分类模型的示例

利用ResNet50网络进行ImageNet分类

利用VGG16提取特征

从VGG19的任意中间层中抽取特征

利用新数据集finetune InceptionV3

在定制的输入tensor上构建InceptionV3

模型文档

参数

返回值

参考文献

License

参数

返回值

参考文献

License

参数

返回值

参考文献

License

参数

返回值

参考文献

License

参数

返回值

参考文献

License

返回值

参考文献

License

引用

猜你喜欢