这是一个简单的示例，可以在我尝试部署的网络中重现我的问题。
我有一个图像输入层（需要维护），然后是一个密集层，Conv2D层和一个密集层。
这个想法是输入是10x10图像，标签是10x10图像。受我的代码和this example的启发。
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())
我收到以下错误：ValueError: Error when checking target: expected dense_92 to have shape (10, 10, 10) but got array with shape (10, 10, 1)
如果进行更改，我不会收到错误消息
outputs = Dense(size, activation='sigmoid')(hidden)
具有：
outputs = Dense(1, activation='sigmoid')(hidden)
不知道Dense(1)的有效性如何以及model.summary()所指示的10x10输出信号指示如何：
_________________________________________________________________
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
答案 0 :(得分：3)
好吧，根据您的评论：
我想做的事不是标准的。我有一组图像，用于 我想找到每个图像的二进制图像，如果 其像素值为1表示该特征存在于输入图像中
像素具有特征的见解都应从 本地信息（由卷积层提取）和全局 密集层提取的信息。
我猜您正在寻找创建两个分支模型，其中一个分支由卷积层组成，而另一个则仅仅是一个或多个彼此重叠的密集层（尽管在我看来，一个卷积网络可能会达到您想要的目的，因为合并池和卷积层以及最后的一些上采样层的组合会以某种方式保留本地和全局信息。要定义这样的模型，您可以像这样使用Keras functional API：
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
__________________________________________________________________________________________________
请注意，这是实现所需内容的一种方法，它可能会也可能不会针对特定问题和您正在处理的数据。您可以修改此模型（例如，删除池化层或添加更密集的层），或完全使用另一种具有不同类型的层的体系结构（例如，上采样，conv2dtrans）以达到更高的准确性。最后，您必须尝试找到理想的解决方案。
编辑：
为完整起见，这里是如何生成数据和拟合网络的方法：
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)