Xiangde Luo

Some questions about Pretrained models.

1

1. The pretrained models you have provided are compressed file, but it cannot be decompressed. And Pytorch can't directly get parameters. 2.def resnet101_ibn_a(pretrained=False, modelpath='./models', **kwargs): """Constructs a ResNet-101 model. Args:...

Hi, all; Recently, we reimplemented 2D and 3D AC loss in different ways, and also introduced a novel term (elastica term) to AC loss [ACELoss](https://github.com/HiLab-git/ACELoss). Xiangde Luo.

Questions about "This output is too large for python process-process communication" during the inference stage.

2

Hi Fabian, I meet a problem when using nnUNet for inference, the log print this sentence "This output is too large for python process-process communication. Saving output temporarily to disk",...

Hi, Liheng, I have some questions about the DropConnect. In your paper you say "DropConnect perturbation, which would change the network structure by dropping its connections" but in your code...