-
## š Bug
I am using `torchmetrics.classification.roc.ROC` as a parent class in another project [1], and I had OOM issues because of the accumulation of preds and targes (when `threshold=None`).
ā¦
-
### Describe the bug
Hi, Anomalib Teams,
Firstly, thanks a lot for providing this wonderful tools!
I'm planning to use it for my current research for long term development.
I'm prototyping ā¦
-
This is more of a question than an issue. It seems that the default setting for my dataset of 10k rows and 45 features results in
and overfitted model. Decreasing the number of max_rounds seems toā¦
-
By request of multiple Schloss Lab members.
It also would be good to show how to pick a good representative seed (i.e. something close to the median AUC / other performance metric) to then plot.
ā¦
-
We need a simple setting to test the plots of a tiny benchmark experiments where everyone can run on a laptop, @schoersch , could you update what I wrong here or give a pointer?
```
git clone gitā¦
-
Hi,
There are several saved model checkpoints under model/ directory. Are these models trained on training data only (el_train.csv), or trained on both training and test data (el_train.csv and el.cā¦
-
Table 1 of the paper contains AUPR and AUROC for open-set segmentation. However, the .py files under the semantickitti_scripts folder do not print AUPR or AUROC at the end of training/evaluation. It ā¦
-
Hello,
when I trained to 600 iterations, prompted this error, I want to ask what is the reason.The training parameters are based on the configuration file. I only changed nb _ memory _ samā¦
-
### Environment test
After the environment setup, I could successfully train the NPT model on the table dataset with the following command.
```
python run.py --data_set boston-housing --exp_eval_eā¦
-
# Dataset information
- I have mostly finished labelling the LOFAR anomaly detection dataset, there are certainly going to be some inconsistencies, but for now it is sufficient
- Classes such as "Hiā¦