search

baccuslab / torch-deep-retina

PyTorch implementation of Deep Retina
MIT License
8 stars 2 forks source link

spatiotemporal filter #4

Open uestcwangxiao opened 11 months ago

uestcwangxiao commented 11 months ago

I was just wondering how do you implement the spatiotemporal filters in the paper. It seems to me that all the convolution modules are conv2D, based on my limited knowledge of pytorch the spatiotemporal filters should be conv3D. Is there anything I'm wrong or missing?

grantsrb commented 11 months ago

The images are all greyscale rather than pixel values. Otherwise you would be correct. In our case, the input depth (traditionally the RGB dimension) is the time dimension.

uestcwangxiao commented 11 months ago

Cool Thank you!