在Keras中实现一个Siamese NN(Implementing a Siamese NN in Keras)

 所以我试图实现关于Siamese神经网络的这篇文章：Sumit Chopra，Raia Hadsell和Yann LeCun（2005） 对歧视性学习相似性度量，应用于面对验证 。 不过，我使用CIFAR10数据集 ，但使用了10个类。 
 
 其中一条腿的规格为方便起见而被复制。 符号：C_x是一个卷积层，S_x是一个子采样层，F_x是一个完全连接的层; 与共享索引x： 
 
 
 
 C1：特征映射：15，内核大小=（7,7） 
 
 
 S2：特征映射：15，视野=（2,2） 
 
 
 C3：特征映射：45，内核大小=（6,6） 
 
 
 S4：特征映射：45，视场=（4,3） 
 
 
 C5：特征映射：250，内核大小=（5,5） 
 
 
 F6（完全连接层）：不。 的单位= 50 
 
 
 我试过的 
 
model = Sequential()

#C1
model.add(Convolution2D(15, 7, 7,
activation='relu',
border_mode='same',
input_shape=input_img_shape))
print("C1 shape: ", model.output_shape)

#S2
model.add(MaxPooling2D((2,2), border_mode='same'))
print("S2 shape: ", model.output_shape)
#...

#C5
model.add(Convolution2D(250, 5, 5, 
activation='relu', 
border_mode='same'))
print("C5 shape: ", model.output_shape)

#F6
model.add(Dense(50))
 
 这会抛出一个很长的错误信息，我认为这是一个重塑错误。 错误的一个片段： 
 
Exception: Input 0 is incompatible with layer dense_13: expected
ndim=2, found ndim=4
 
 我知道这个问题在最后的Dense层中是孤立的，因为如果我将它注释掉，代码会顺利进行。 但我不确定我应该如何设计/指定我的最终完全连接图层，以便它与先前的卷积图层兼容？ 
 
 我看过的一些地方 
 
 这是一个相关的问题，虽然实现有些不同（在撰写本文时，似乎并没有keras中的'Siamese'核心层）。 我知道在Theano中也有实现，如果我不能在keras中实现 ，我会记住它。 
 
 谢谢！ 

So I'm trying to implement this paper about a Siamese neural network: Learning a similarity metric discriminatively, with application to face verification, by Sumit Chopra, Raia Hadsell and Yann LeCun (2005). I'm using the CIFAR10 dataset instead, though, with 10 classes. 
 
The specifications of one of the legs is reproduced for convenience. Notation: C_x is a convolution layer, S_x is a subsampling layer and F_x is a fully connected layer; with a shared index x:
 
 
 
C1: feature maps: 15, kernel size = (7, 7)
 
 
S2: feature maps: 15, field-of-view = (2, 2)
 
 
C3: feature maps: 45, kernel size = (6, 6)
 
 
S4: feature maps: 45, field-of-view = (4, 3)
 
 
C5: feature maps: 250, kernel size = (5, 5)
 
 
F6 (fully connected layer): no. of units = 50
 
 
What I've Tried
 
model = Sequential()

#C1
model.add(Convolution2D(15, 7, 7,
activation='relu',
border_mode='same',
input_shape=input_img_shape))
print("C1 shape: ", model.output_shape)

#S2
model.add(MaxPooling2D((2,2), border_mode='same'))
print("S2 shape: ", model.output_shape)
#...

#C5
model.add(Convolution2D(250, 5, 5, 
activation='relu', 
border_mode='same'))
print("C5 shape: ", model.output_shape)

#F6
model.add(Dense(50))
 
This throws a long error message, which I believe is a reshape error. A snippet of the error:
 
Exception: Input 0 is incompatible with layer dense_13: expected
ndim=2, found ndim=4
 
I know that the problem is isolated in that final Dense layer, because the code proceeds smoothly if I comment it out. But I'm not sure exactly how I should then shape/specify my final fully connected layer so that it's compatible with the prior convolution layer?
 
Some Places I've Looked
 
This is a related problem, though the implementation is slightly different (it seems that there isn't a 'Siamese' core layer in keras at the time of this writing). I'm aware that there are also implementations in Theano, which I'll bear in mind if I'm just not able to do it in keras.
 
Thanks!

原文：https://stackoverflow.com/questions/38584268