-
### 🐛 Describe the bug
Dataset is not undirected, despite passing ``to_undirected=True`` flag.
```python
# !pip install pyg-nightly
from torch_geometric.datasets import CitationFull
from torc…
-
### 🐛 Describe the bug
Using MPS for BERT inference appears to produce about a 2x slowdown compared to the CPU. Here is code to reproduce the issue:
```python
# MPS Version
from transformers i…
-
-
0. SCREENSHOTS.
![image](https://github.com/NLP-Suite/NLP-Suite/assets/142829954/27089259-0430-…
-
-
no matter which version I try it always crash just after "loading world" Here is the log:
[27Jul2024 20:08:21.948] [main/INFO] [cpw.mods.modlauncher.Launcher/MODLAUNCHER]: ModLauncher running: args…
-
First, I want to say that I am aware of the existing [reproducibility issues with scatter ops](https://github.com/pyg-team/pytorch_geometric/issues/92).
But still, I expect that those numerical issue…
-
@qiaoyu-tan I’m trying to run this code as a baseline of our work. Nevertheless, the link prediction task needs the social network datasets in MATLAB format and they’re not provided apart from Cora. I…
-
I want to use GCN to build my own network, but I don't know how to make my own data set. For example, I run pytorch_geometric-master/examples/gcn.py and use the'Cora'data set here, but if I want to …
-
hello, I would like to ask for advice.
In the node classification problem, the dataset used is Cora
Every time I run it, it prompts me with this problem, how should I change it?
`
RuntimeError: Th…