-
Hi, I have a question on the module in your paper, which says "apply a Diffpool layer after two Graphsage layers", "A total of 2 Dffpool layers are used ", "After each Diffpool layer, 3 layers of gra…
-
Hi, I used the same codes and datasets to tune the parameters provided by the paper. The random seed is set by 0. The followings are the results:
![image](https://user-images.githubusercontent.com…
-
1.TexturePose: Supervising Human Mesh Estimation with Texture Consistency(2019)
Texture map (texel): A corresponding UVmap un-warps the template surface onto an image, A, which is the texture map
co…
-
Dear Author,
I could reproduce task including MYTAG,PTC,NCl1,PROTEINS,IMDB-B,IMDB-M,RDT-M5K using the parameters of your paper, however, I could not reproduce the results for RDT-B and COLLAB usin…
-
Hi @RexYing!
Thank you for the great package, I really enjoyed reading the paper as well.
I'm thinking of applying your explanation model to a deep graph CNN that I trained on a graph classific…
-
hi:
i trans model.ckpt to .pb according to [https://github.com/zengarden/light_head_rcnn/issues/66](url)
but when i start inference function , it raise such error:
> Traceback (most recent call l…
-
I'm able to build and display a graph right away on the torchvision `alexnet` model. But on the torchvision `vgg16_bn` model, if try to graph the model before training I get the error, `ValueError: Ex…
-
This is an enlightening paper. Thank you for your sharing, which gives me the opportunity to study the paper in depth!
When I ran graph.py, an NameError occurred in line 215 ,pool=Pool_layer(poolin…
-
Hi,
Thanks for making the source of HGT public.
A question that I have is that how can we use HGT to classify heterogeneous graphs?
Currently, the training examples that are provided are for node…
-
Hi Matt,
I have question about designing a simple pooling layer from some `GCNConv` layers.
I would like to create a supervised regression model. I have many number of graphs in the datasets, an…