WillRobert

Subtraction, the `-` operator, with a bool tensor is not supported.

1

When I try to feed the cheb_conv with SparseTensor, I got the following errors: ``` x = self.model(x, sparse_adj_mat) File "/home/user/miniconda2/envs/myenvlib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File...

RGB vs all-one vector features

1

Should we expect to get better performance when add RGB as the feature in the sparse tensor? For my application, instead I found performance drop when using RGB ( I...

Since FGR is global registration algorithm, initial pose is not necessary. Does the algorithm work when the target point cloud is rotated by 90 degrees or more? I am working...

Different results on two machines

1

Hi, thanks for this nice code. I run the code on two machines with the same pytorch version but got garbage values on one of them. Here is the set...

Hi, I am making a simple experiment in which GCN is used to predict node degree (it sounds silly to do that as node degree is easy to compute; it...

where is "s2s"

1

I am assuming it is a package as I didn't find a file named "s2s". Could you provide a list of required packages in order to run the code?

Adaptive AvgPool

3

Could you support AdaptiveAvgPool similar to nn.AdaptiveAvgPool2d?

When evaluating performance on KITTI depth data, are you using raw sparse lidar measurements, or post-processed dense depth map as ground truth?

Do you have evaluated Eagle models on object detection tasks? Like coco dataset.