Closed baoruxiao closed 6 years ago
SENet is constructed by integrating SE blocks to a modified version of the 64x4d ResNeXt-152., so the model size and computation are much bigger than SE-ResNeXt-101. More details about SENet are described in Appendix A. of the paper.
Hi Hujie,
I wonder what is the architectural difference between SE-ResNeXt-101 and SENet, I have OOM issue with SENet and it almost require 7G to initialize the network, but SE-ResNeXt-101 only need <3G. Why there is hug memory usage difference?
Please help.
Thanks, Ruxiao