-
## ❓ Questions/Help/Support
Hi, support teams.
This is my first time asking a question.
I believe the following code will load the checkpoints.
==================================================…
-
Hi, I have installed the code in python3.8, pytorch 1.8.0 and cuda11. And the debug_relationformer.ipynb runs well about Debug Dataloader and Debug Model part.
However, when I run the train.py using …
-
## 🐛 Bug
## To Reproduce
You can reproduce the problem through the following code:
```
from torch import nn
m = nn.AdaptiveMaxPool2d((5,7))
input = torch.randn(1, 64, 8, 9)
output = m…
-
# 🐛 Bug
When try to install xformers from pip, the installation frozeen to 100% of CPU for > 30 minutes (I stopped it before finish)
## Command
## To Reproduce
pip install xformers
Steps to…
-
## 🐛 Bug
Discovered by @ngimel
code
```python
import torch
print(torch.__version__)
print(torch.version.cuda)
b = torch.nn.Conv2d(32, 32, 2, bias=False, padding=1)
a = torch.randn(2, 32…
-
## 🐛 Bug description
Below code shows the error:
```python
from ignite.engine import Engine, Events
from ignite.utils import setup_logger
stop_iter = 50
epoch_length = 100
max_epochs = 2
…
-
### 🐛 Describe the bug
It seems that a constraint reparametrization breaks if one uses `F.sigmoid` instead of `torch.sigmoid`. I know the former is deprecated but I am still curious as to why it is…
-
## ❓ Questions/Help/Support
I'm really new to the ML area and I'm trying to train a network with a dataset that when sampling batches, it can create batches with really large sizes (the sampling me…
-
**Describe the bug**
Before I got to update my cudatoolkit 11.8 MonaiLabel was not recognizing cudatoolkit 11.3 and cuda was disabling. The training process was ran in CPU mode and was running fine.…
-
## 🚀 Feature
Idea is to simplify user's learning curve and provide a template example that can be copied by the user and modified to his/her needs. Something like that but an executable working exa…