Tong

I have the same issue. I found _positional gene sets, motif gene sets and immunological signatures_ in this GSEA database: http://www.gsea-msigdb.org/gsea/msigdb/index.jsp, but I don't know how to process these information...

Thanks:) I will have a try.

It works. Thanks a lot!

I see, "Despite the VAE in Diffusion training being frozen" mentioned in your latest doc. Is that means that you've found freezing 2d-VAE weight ("tail" of casual3d Conv) performs better?

> @vivym Do you train the full model? or freeze the model, just train the temporal block? I've tried train the full model, the motion blurring is alleviated, while the...

> I have a question on the feature sets. As the dimensions of c1, c3, c7 are very large, how did you represent each protein using 50-dimensional vectors? > >...

I have the same problem and solve it. Maybe the reason is the different version of test and train.lst file. For me, after `path_names = path.split('/')`, path_names = ['DATASET', 'DeepFashion_highres',...

For [MUTAG in PYG](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.datasets.Entities.html#torch_geometric.datasets.Entities): there is only ONE graph, with "edge index" and "edge type" information. According to the documentation, the data processing comes from [Modeling Relational Data with Graph...

Thank you for your answer, I found that this issue has been resolved. The dataset used in GNNExplainer is called **Mutagenicity**, not MUTAG. They are two different dataset according to...

you can refer to this: https://github.com/threestudio-project/threestudio/issues/266. \delta sds_loss / \delta z will direcly be the grad_z (e_t - eps), which can avoid Unet backward required for Chain Rule.