-
I am trying to use a series of graph convolution layers on a custom dataset (say 400 nodes) for producing embeddings using modularity-based communities as in the Karate Club example. This is just an e…
-
Hi, I'm interested in this work. But I don’t know what is the use of generate_indices for spa_mask.
-
**Describe the bug**
When I try to convert the onnx model [emotion_ferplus](https://github.com/onnx/models/tree/master/emotion_ferplus) to TensorFlow, I get an error.
Shortened, presumably relev…
-
I have noticed that using sparse matrices with a DataLoader works only if num_processes = 0.
Example:
```
import torch
from torch.utils.data import DataLoader
print('torch version: ', torch…
-
-
Just tried to use HMatrix on current DragonflyBSD. Here's what I see. (My file `nc.cabal` lists `hmatrix` as a dependency.)
This seems similar to #125. I guess `struct random_data` is a Linux-only …
-
**Describe the bug**
When the summary on the Graph Convolutional Networks model is called and the model input is provided, the output summary doesn't contain any numbers in the column "Param #".
**T…
-
Can you provide pretrained model on waymo dataset and some guides for running the inference code? Although there is README file for using the sparse conv, i still stuck in runing the inference code. …
-
[Maurer et al](https://fadibarbara.it/papers/Anonymous_CoinJoin_Transactions_with_Arbitrary_Values.pdf)'s sub-transaction mappings model quantifies the relatedness of inputs and outputs of a transacti…
-
Hi,
Thanks for your work.
What's main difference between VOLO and DynamicConv?
Though `Convolution` is not explicitly used,
**Convolution is equivalent with Unfold + Matrix Multiplication +…