-
## 🚀 Feature
Cross-Validation is a crucial model validation techniques for assessing how the model generalizes on new data.
### Motivation
Research papers usually require cross-validation. Fro…
-
The results for ranking are thus:
With the following votes…
-
### Bug description
This is technically not a bug but I couldn't find a more appropriate tag.
https://github.com/Lightning-AI/lightning/blob/d5ffdfac2ad4c8ff87c9895555fc21ccc482c18c/src/pytorch_…
-
After commit [1c46c1f](https://github.com/julien-boudry/Condorcet/commit/1c46c1f2d217315be8d118dc10c78799d7cee27e), various test failures show that various methods are outputting the wrong results in …
-
### Bug description
Hi all,
I recently tried to implement a DeepLabV3 training pipeline. I wanted to use the build-in `torchmetrics.JaccardIndex` as my evaluation metric. My `LightningModule` l…
-
### Bug description
With `precision=32` in the Trainer, a `RuntimeError` occurs after the last `training_step` before optimization. The runtime error appears to be associated with `torch.is_grad_en…
-
1- I can't access the research paper associated with BORDA on the pyDecision website.
2- Is this method the same as BORDA Count ?
3- Why are the alternatives with lowest value ranked first ?
4- If …
-
#### tl;dr
does the approach in the code snippet below look ok, or is there a better alternative for automatically skipping few "bad" samples in the data that cause inf/nan gradients/loss? (is it a g…
-
## 🐛 Bug
The `QuantizationAwareTraining` can only handle models whose forward signature looks like `forward(data)`. Adding additional positional or keyword arguments breaks the forward propagation.…
-
## 🚀 Feature
First, we are very happy about all your contribution that the community-made so far! Unfortunately, we are getting a bit short :(
Second, we would like to re-ignite this project/repos…