Closed Fangyu-ict closed 4 years ago
Thanks for your interest. The CWI operation aims to align the shape of different feature maps. For example, to aggregate two feature maps A in R^{HWC1} and B^{HWC2}, you can not weighted-sum them due to the inconsistent shape. So we use CWI (https://github.com/D-X-Y/NAS-Projects/blob/master/lib/models/shape_searchs/SoftSelect.py#L41) to align their shapes.
Thanks.
Hi, thanks for your great work.
After reading your paper TAS, I don't understand the channel-wise interpolation. Could you explain or give an insight on channel-wise interpolation (i.e., making weighted sum on feature maps of different sizes), and the corresponding effects.
Thanks.