Reputation: 384
How is kernel size in keras convolution layers defined?
According to the documentation website (https://keras.io/layers/convolutional/) the kernel size of a keras convolution layer is defined as height x width:
kernel_size: An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
In the code documentation however it is defined as the exact opposite:
kernel_size: An integer or tuple/list of 2 integers, specifying the width and height of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.
Which one is true? As far as I figured out, the definition of the website should be the right one, am i right?
Upvotes: 2
Views: 5533
Answers (1)
Reputation: 6044
Yes, the definition in the website is correct (height x width). The code documentation was fixed in version 2.2.0 as per this commit.
Upvotes: 1
Related Questions
- Keras conv1d layer parameters: filters and kernel_size
- When and why kernel_size may be 1 or 2 dims when using Conv2D?
- conv1D kernel size in Keras
- Kernel Size Defining and Activation Function in Keras
- Why is CNN convolution output size in PyTorch DQN tutorial computed with `kernel_size -1`?
- Keras Conv2D: filters vs kernel_size
- Is there any criterion for deciding the kernel size of convolutional layer and pooling layer?
- How does Keras set the dimensions in this network which has CNN and dense layers?
- Relation between kernel size and input size in CNN
- CNN architecture - how to interpret kernel size notation