Using conv1d with kernel size 1

Question

Using conv1d with kernel size 1

ollmer opened this issue 6 years ago · 2 comments

Hi!
I've noticed that the training code using 1d convolution with kernel size 1 in all invocations. Do we need convolution at all here? Why not replace it with the fully_connected layer?

Answer 1 · 2018-08-14T05:14:52.000Z

If my understanding is correct, using a 1D convolution is the same as taking a dot product between the original matrix (say of dimensions n_timesteps x d) and a matrix of dimension d x n_filters.

Answer 2 · 2018-08-30T18:43:45.000Z

The codebase uses matmul when the receptive field size is 1. I originally thought conv1d would do this automatically "under the hood" but that does not appear to be the case.