-
**Describe the bug**
The `q` parameter does not receive gradient even when `trainable_q = True` in `MagNet_link_prediction` .
**To Reproduce**
The following MWE (taken from [here](https://github…
-
Version:
```
torch==1.13.0
torch-geometric==2.3.0
torchdrug==0.2.0
```
Code:
```
import torch_geometric
```
Output:
```
----------------------------------------------------------------…
tsa87 updated
6 months ago
-
your code can't run due to lack of the code in torch_geometric. Can you provide the code?
-
### 🐛 Describe the bug
The current implementation of the Kumaraswamy distribution has significant numerical instabilities in its log-pdf, inverse CDF, and their parameter gradient expressions. All su…
-
Hi! Thanks for this library :)
I'm trying to use InstanceNorm and it appears there's a bug.
When I run the following
```python
irreps = BalancedIrreps(3, 20)
norm = InstanceNorm(irreps)
x = torc…
pimdh updated
1 month ago
-
### 🐛 Describe the bug
Dear pyg-lib team,
I encountered an error when I call.
```
out = torch.ops.pyg.merge_sampler_outputs(
sampled_nodes_with_dupl,
edge_ids,
…
-
### 😵 Describe the installation problem
Hello, when I use the command”from torch_geometric.loader import DataLoader“ , I will report an error”ModuleNotFoundError: No module named 'torch_geometric.loa…
-
The current instructions for creating a conda environment does not work. In particular, issues arise with pytorch and pytorch-geometric. I have attempted installing with pip instead using:
```
pi…
-
From readme instructions, I tried the listed examples: `python gnn_node.py --dataset rel-f1 --task driver-position` , and also:
`python gnn_node.py --dataset rel-avito --task ad-ctr`
My environme…
-
despite having installed torch-cluster version properly i still got this error message .... could help plz ?
Pip subprocess error:
ERROR: Could not find a version that satisfies the requirement t…