CHIP_NeurIPS2021
CHIP_NeurIPS2021 copied to clipboard
Why is the resnet_56 model composed of basic blocks?
First of all, I appreciate your great work.
As far as I know, generally, resnet_56 for the CIFAR10 dataset is composed of bottleneck blocks. However, the resnet_56 model in this code is composed of basic blocks. And HRank, too.
Is there any reason to build the resnet_56 model like this?
Resnet_56 contains the basic blocks. Resnet50 is composed of bottleneck blocks.