CODEWITHSUNDEEP
kerasregressionconv-neural-network
Rutger Hofste
Rutger Hofste

Reputation: 4373

which settings to use in last layer of CNN for regression

I try to use a CNN for a regression task.

My feature data has shape (6097, 30, 32, 9):

the target data has shape
(6097, 1)

When I create the last Dense layer of my CNN regression model, I am not sure which settings to use. The output dimension of the last convolution layer is (None,2,2,512). I've added a BatchNorm and Flatten layer (not sure if this makes sense)

What is the correct number of units and the activation function? My guess is units=1 and activation function = "None"

Keras:

model.add(Dense(units=1,
                activation=None
                ))

enter image description here

Upvotes: 2

Views: 2192

Answers (1)

a-doering
a-doering

Reputation: 1179

That depends on the kind of result you want, often times a linear activation function is used to simply map the value back (it does not change it). Here is a brief explanation on the choice in the output layer. Here is an explanation on regression that also briefly mentions the output layer. The amount of units was already correct.

model.add(Dense(units=1,
                activation='linear'
                ))

Or for the same result:

model.add(Dense(1))

Upvotes: 3

Related Questions