代码之家 › 专栏 › 技术社区 › 0x90 Salvador Dali

如何在keras中构建一个“Input->Dense->Conv2D->Dense”网络?

conv-neural-network keras tensorflow python

0x90 Salvador Dali · 技术社区 · 6 年前

这是一个简单的例子,在我试图部署的网络中重现了我的问题。

我有一个图像输入层(我需要维护),然后是密集层,Conv2D层和密集层。

import numpy as np
from keras.models import Model
from keras.layers import Input, Conv2D

#Building model
size=10
a = Input(shape=(size,size,1))
hidden = Dense(size)(a)
hidden = Conv2D(kernel_size = (3,3), filters = size*size, activation='relu', padding='same')(hidden)
outputs = Dense(size, activation='sigmoid')(hidden)

model = Model(inputs=a, outputs=outputs)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

#Create random data and accounting for 1 channel of data
n_images=55
data = np.random.randint(0,2,(n_images,size,size,1))
labels = np.random.randint(0,2,(n_images,size,size,1))

#Fit model
model.fit(data, labels, verbose=1, batch_size=10, epochs=20)

print(model.summary())

我得到以下错误: ValueError: Error when checking target: expected dense_92 to have shape (10, 10, 10) but got array with shape (10, 10, 1)

outputs = Dense(size, activation='sigmoid')(hidden)

使用:

outputs = Dense(1, activation='sigmoid')(hidden)

Dense(1) 甚至是有效的,它如何允许10x10输出信号作为 model.summary() 表示:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_26 (InputLayer)        (None, 10, 10, 1)         0         
_________________________________________________________________
dense_93 (Dense)             (None, 10, 10, 10)        20        
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 10, 10, 100)       9100      
_________________________________________________________________
dense_94 (Dense)             (None, 10, 10, 1)         101       
=================================================================
Total params: 9,221
Trainable params: 9,221
Non-trainable params: 0
_________________________________________________________________
None

1 回复 | 直到 6 年前

0x90 Salvador Dali 6 年前

好吧,根据你的评论:

我想做的不是标准的。我有一套图像和每个图像我想找到一个二值图像的大小相同,如果它的像素值为1,表示该特征存在于输入图像中

一个像素是否有一个特征的洞察力应该从两个方面来考虑由密集层提取的信息。

我猜你正在寻找一个两分支模型,其中一个分支由卷积层组成,而另一个分支仅仅是一个或多个相互重叠的密集层(尽管,我应该提到,在我看来,一个卷积网络可以实现你所寻找的,因为池层和卷积层的组合以及最后的一些上采样层在某种程度上保留了局部和全局信息)。要定义这样的模型,可以使用 Keras functional API 这样地:

from keras import models
from keras import layers

input_image = layers.Input(shape=(10, 10, 1))

# branch one: dense layers
b1 = layers.Flatten()(input_image)
b1 = layers.Dense(64, activation='relu')(b1)
b1_out = layers.Dense(32, activation='relu')(b1)

# branch two: conv + pooling layers
b2 = layers.Conv2D(32, (3,3), activation='relu')(input_image)
b2 = layers.MaxPooling2D((2,2))(b2)
b2 = layers.Conv2D(64, (3,3), activation='relu')(b2)
b2_out = layers.MaxPooling2D((2,2))(b2)

# merge two branches
flattened_b2 = layers.Flatten()(b2_out)
merged = layers.concatenate([b1_out, flattened_b2])

# add a final dense layer
output = layers.Dense(10*10, activation='sigmoid')(merged)
output = layers.Reshape((10,10))(output)

# create the model
model = models.Model(input_image, output)

model.compile(optimizer='rmsprop', loss='binary_crossentropy')
model.summary()

模型摘要:

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (None, 10, 10, 1)    0                                            
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (None, 8, 8, 32)     320         input_1[0][0]                    
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D)  (None, 4, 4, 32)     0           conv2d_1[0][0]                   
__________________________________________________________________________________________________
flatten_1 (Flatten)             (None, 100)          0           input_1[0][0]                    
__________________________________________________________________________________________________
conv2d_2 (Conv2D)               (None, 2, 2, 64)     18496       max_pooling2d_1[0][0]            
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 64)           6464        flatten_1[0][0]                  
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D)  (None, 1, 1, 64)     0           conv2d_2[0][0]                   
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 32)           2080        dense_1[0][0]                    
__________________________________________________________________________________________________
flatten_2 (Flatten)             (None, 64)           0           max_pooling2d_2[0][0]            
__________________________________________________________________________________________________
concatenate_1 (Concatenate)     (None, 96)           0           dense_2[0][0]                    
                                                                 flatten_2[0][0]                  
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 100)          9700        concatenate_1[0][0]              
__________________________________________________________________________________________________
reshape_1 (Reshape)             (None, 10, 10)       0           dense_3[0][0]                    
==================================================================================================
Total params: 37,060
Trainable params: 37,060
Non-trainable params: 0
__________________________________________________________________________________________________

编辑:

为了完整起见,这里介绍了如何生成数据和拟合网络:

n_images=10
data = np.random.randint(0,2,(n_images,size,size,1))
labels = np.random.randint(0,2,(n_images,size,size,1))
model.fit(data, labels, verbose=1, batch_size=32, epochs=20)