bmsookim / wide-resnet.pytorch

Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch
MIT License
462 stars 129 forks source link

These ResNets are not for CIFAR10 #4

Open PabloRR100 opened 6 years ago

PabloRR100 commented 6 years ago

The ResNets from the authors on the original paper change the sizes when applied to CIFAR10. It just don't match the dimensions you specified here:

ResNets for CIFAR10 are 2+6n layers leading to architectures: ResNet20, ResNet32, ResNet44, ResNet56, ResNet110, ResNet1202. This is mixed up with ResNets for ImageNet datasets but the models should not be the same.

Furthermore, in the paper they don't use neither BasicBlock or BottleneckBlock. They just pad the input volume to match the dimensions before summation every 2n layers, when a downsampling is performed by a stride of 2