I have a convolutional layer $g$ with 10 feature maps given by: $$g(x^i) = \sigma([z_1,z_2,\dots,z_{10}])$$ where $z_j = f(x^i,w_j)$ is the output of a 1-d convolutional operation parameterized by a filter $w_j$ of size 3. Each $x^i$ is padded with a zero at each end. And $x^i$ is a set of 1-D signals in $R^{100}$.

I'm trying to figure out what would be the input size and output size of this convolutional layer.

How can I approach this?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.