Simon

Hey zhanghuanrong, the kernel is called _ResizeNearestKernel and it spend 58ms seconds there (after having several warmup inference runs) when resizing the `Tensor[1, 128, 48, 48, 48]`. I also resize...

hi @zhanghuanrong , thank you for looking into this. I was just wondering if you could provide an update on this. It'd be great if you could give an estimate...

Hey, I was wondering if there is any news on this. We'd like to move foreward with our release soon so if it's not possible to fix this, I'd like...

I've updated the title since indd overall, onnxruntime seems to be faster but the Rescale operator for 3D tensors is significantly slower than the one in pytorch. The reason for...

Thank you for adding it to the milestone. I ported the pytorch implementation as a custom operator. It is however quite hacky and only works for our use case so...

Hey, I was wondering if there is an update on the status of this issue? Was this resolved in 1.19? We might want to upgrade our onnxruntime version and it...

Hey, I've tried switching to 12.8 but now I get the following error. I'm still using v1.22.0 ``` C:\Users\Administrator\Documents\GitHub\onnxbuilder\onnxruntime\onnxruntime\core\optimizer\graph_transformer_utils.cc(1 97,63): error C2220: the following warning is treated as an error...

> It would be really nice to have access/proxy through the 1Password-BrowserSupport.sock into the remote container to allow running op without any workarounds but linked to the host's biometrics. >...