Questions tagged [feature-maps]
For questions related to the concept of a feature map in the context of convolutional neural networks.
7
questions
0
votes
2
answers
639
views
How do we combine feature maps? CNN
In Convolutional Neural Networks we extract and create abstractified “feature maps” of our given image. My thought was this: We extract things like lines initially. Then from different types of lines ...
0
votes
1
answer
195
views
combine two features in dataset?
I have a data set containing the number of security gaps and the level of that gap for a specific website.
Now suppose I have 2 features in this data set, the first feature is the number of a ...
1
vote
0
answers
41
views
What are the recommended ways to change shape of feature maps channel wise other than using Convolutional neural networks?
Suppose I have a feature map with size $C_1 \times H \times W$. And I need to convert it into a feature map of size $C_2 \times H \times W$.
One way to do this is to use convolutional neural networks ...
- 3,612
1
vote
1
answer
1k
views
How is the depth of the filters of convolutional layers determined? [duplicate]
I am a bit confused about the depth of the convolutional filters in a CNN.
At layer 1, there are usually about 40 3x3x3 filters. Each of these filters outputs a 2d array, so the total output of the ...
- 793
16
votes
1
answer
5k
views
What is the difference between a receptive field and a feature map?
In a CNN, the receptive field is the portion of the image used to compute the filter's output. But one filter's output (which is also called a "feature map") is the next filter's input.
What's the ...
- 261
7
votes
2
answers
177
views
CNNs: What happens from one neuron volume to the next?
I've gone through several descriptions of CNNs online and they all leave out a crucial part as if it were trivial.
A "volume" of neurons consists of several parallel layers ("feature ...
- 181
3
votes
3
answers
6k
views
How is the depth of a convolutional layer determined?
I am looking at a diagram of ZFNet below, in an attempt to understand how CNNs are designed.
In the first layer, I understand the depth of 3 (224x224x3) is the number of color channels in the image.
...
- 133