torchmetrics icon indicating copy to clipboard operation
torchmetrics copied to clipboard

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

Results 208 torchmetrics issues
Sort by recently updated
recently updated
newest added

### Discussed in https://github.com/PyTorchLightning/metrics/discussions/965 Originally posted by **iamharsha1999** April 19, 2022 I was specifically looking for the following two metrics: 1. Sensitivity at Specificity 2. Specificity at Sensitivity However I...

enhancement
New metric

## 🚀 Feature Add `DepthScore` ### Sources: - Paper: [A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions ](https://arxiv.org/pdf/2103.12711.pdf) - [Repo](https://github.com/PierreColombo/nlg_eval_via_simi_measures/) ### Motivation The recent NLG metrics are more often...

enhancement
New metric
topic: Text

## 📚 Documentation There's something wrong with metrics source redirect: 1. On `stable`, If you click on source, it doesn't show up anything on master which is fine I guess...

documentation

## 🚀 Feature I want to calculate `edit_distance` between two strings. I would prefer an API similar to [NLTK.metrics](https://www.nltk.org/api/nltk.metrics.distance.html#module-nltk.metrics.distance) ### Motivation ### Pitch ```python from torchmetrics.functional import edit_distance text1 =...

enhancement
New metric

## What does this PR do? This PR adds a new metric Relative Average Spectral Error (RASE), and Root Mean Squared Error using Sliding Window the metric RASE is based...

New metric

## What does this PR do? This PR is currently heavilly WIP. This PR adds a new NLP metric `METEORScore` according to version 1.5 [Meteor Universal: Language Specific Translation Evaluation...

New metric
topic: Text

## What does this PR do? Adds in IOU and GIOU metrics for object detection. Fixes #659 I took a first attempt at this PR and there are a few...

New metric

## 🚀 Feature Metric states seem to be limited to `torch.Tensor` or `List[torch.Tensor]`. In my usecase i want to store a dictionary as state. My dataset comprises of samples who...

enhancement
question

## 🚀 Feature Generalized Dice Score (= 1 - [Generalized Dice Loss](https://arxiv.org/abs/1707.03237)), to evaluate overall segmentation performance in multiclass scenarios. ### Motivation Nice complement to Dice Score. ### Pitch Addition...

enhancement
New metric

## 🐛 Bug So I'm not entirely sure whether this is a bug or intentional, in that case this would be a doc fix request. As the title states, the...

bug / fix
help wanted