Google inception
GoogLeNet的inception是一个相对比较复杂的拼接网络，我们用函数式模型来完成一下
from keras.layers import Conv2D, MaxPooling2D, Input
input_img = Input(shape=(3, 256, 256))
tower_1 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3, 3), padding='same', activation='relu')(tower_1)
tower_2 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5, 5), padding='same', activation='relu')(tower_2)
tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(64, (1, 1), padding='same', activation='relu')(tower_3)
output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
ResNet
残差网络（Residual Network）是一个带高速通道的网络，可以考虑下面的函数式模型实现
from keras.layers import Conv2D, Input
# input tensor for a 3-channel 256x256 image
x = Input(shape=(3, 256, 256))
# 3x3 conv with 3 output channels (same as input channels)
y = Conv2D(3, (3, 3), padding='same')(x)
# this returns x + y.
z = keras.layers.add([x, y])
共享视觉模型
该模型在两个输入上重用了图像处理的模型，用来判别两个MNIST数字是否是相同的数字
from keras.layers import Conv2D, MaxPooling2D, Input, Dense, Flatten
from keras.models import Model
# First, define the vision modules
digit_input = Input(shape=(1, 27, 27))
x = Conv2D(64, (3, 3))(digit_input)
x = Conv2D(64, (3, 3))(x)
x = MaxPooling2D((2, 2))(x)
out = Flatten()(x)
vision_model = Model(digit_input, out)
# Then define the tell-digits-apart model
digit_a = Input(shape=(1, 27, 27))
digit_b = Input(shape=(1, 27, 27))
# The vision model will be shared, weights and all
out_a = vision_model(digit_a)
out_b = vision_model(digit_b)
concatenated = keras.layers.concatenate([out_a, out_b])
out = Dense(1, activation='sigmoid')(concatenated)
classification_model = Model([digit_a, digit_b], out)
视觉问答模型
在针对一幅图片使用自然语言进行提问时，该模型能够提供关于该图片的一个单词的答案
这个模型将自然语言的问题和图片分别映射为特征向量，将二者合并后训练一个logistic回归层，从一系列可能的回答中挑选一个。
from keras.layers import Conv2D, MaxPooling2D, Flatten
from keras.layers import Input, LSTM, Embedding, Dense
from keras.models import Model, Sequential
# First, let's define a vision model using a Sequential model.
# This model will encode an image into a vector.
vision_model = Sequential()
vision_model.add(Conv2D(64, (3, 3) activation='relu', padding='same', input_shape=(3, 224, 224)))
vision_model.add(Conv2D(64, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
vision_model.add(Conv2D(128, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
vision_model.add(Conv2D(256, (3, 3), activation='relu'))
vision_model.add(Conv2D(256, (3, 3), activation='relu'))
vision_model.add(MaxPooling2D((2, 2)))
vision_model.add(Flatten())
# Now let's get a tensor with the output of our vision model:
image_input = Input(shape=(3, 224, 224))
encoded_image = vision_model(image_input)
# Next, let's define a language model to encode the question into a vector.
# Each question will be at most 100 word long,
# and we will index words as integers from 1 to 9999.
question_input = Input(shape=(100,), dtype='int32')
embedded_question = Embedding(input_dim=10000, output_dim=256, input_length=100)(question_input)
encoded_question = LSTM(256)(embedded_question)
# Let's concatenate the question vector and the image vector:
merged = keras.layers.concatenate([encoded_question, encoded_image])
# And let's train a logistic regression over 1000 words on top:
output = Dense(1000, activation='softmax')(merged)
# This is our final model:
vqa_model = Model(inputs=[image_input, question_input], outputs=output)
视频问答模型
在做完图片问答模型后，我们可以快速将其转为视频问答的模型。在适当的训练下，你可以为模型提供一个短视频（如100帧）然后向模型提问一个关于该视频的问题，如“what sport is the boy playing？”->“football”
from keras.layers import TimeDistributed
video_input = Input(shape=(100, 3, 224, 224))
# This is our video encoded via the previously trained vision_model (weights are reused)
encoded_frame_sequence = TimeDistributed(vision_model)(video_input) # the output will be a sequence of vectors
encoded_video = LSTM(256)(encoded_frame_sequence) # the output will be a vector
# This is a model-level representation of the question encoder, reusing the same weights as before:
question_encoder = Model(inputs=question_input, outputs=encoded_question)
# Let's use it to encode the question:
video_question_input = Input(shape=(100,), dtype='int32')
encoded_video_question = question_encoder(video_question_input)
# And this is our video question answering model:
merged = keras.layers.concatenate([encoded_video, encoded_video_question])
output = Dense(1000, activation='softmax')(merged)
video_qa_model = Model(inputs=[video_input, video_question_input], outputs=output)