Caenorst
Caenorst
@guillochon v0.16.0 now have wheels support for 3.11, unfortunately usd-core is not supporting 3.12 yet, but I will update once it does.
I rotate and flip them the same way because it's just easier to do (it doesn't really matter there is no real dependencies between cover and stego when you use...
Hi, > in train_loader, pair_constraint=not(args.use_batch_norm), Why set pair_constraint as False when use batch normalization? First of all the original publication doesn't use batch normalization. If you want to use it,...
Hi, The publication use BOSSbase_1.01 + BOWS2. With my current implementation you can use any dataset. Just put the training and validation cover images et stego images in separate files
Hi Alexander, Good catch! Actually the Kaolin App in Omniverse is deprecated. You can still visualize any USD generated by Kaolin in Omniverse USD explorer. Will fix soon. The Kaolin...
Can you force push to trigger the CI ?
Hi @haonanhe , unfortunately our `_C.ops.mesh.unbatched_mesh_intersection_cuda` doesn't expose the position of intersection, if you feel CUDA savyy you can modify the kernel and make expose the intersection (and feel free...
Hi @ansorre , we will definitely support 2.6.0 for next release!
Yes, in general we always try to support the latest of pytorch at release. Expect whatever latest pytorch to be supported for next release. We should have one soon. If...
Hey everyone, kaolin v0.18.0 support pytorch 2.6.0 now !