-
-
Save c3333/04b9cfd40f948f2967b50274e16b97f1 to your computer and use it in GitHub Desktop.
F1 score in PyTorch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def f1_loss(y_true:torch.Tensor, y_pred:torch.Tensor, is_training=False) -> torch.Tensor: | |
'''Calculate F1 score. Can work with gpu tensors | |
The original implmentation is written by Michal Haltuf on Kaggle. | |
Returns | |
------- | |
torch.Tensor | |
`ndim` == 1. 0 <= val <= 1 | |
Reference | |
--------- | |
- https://www.kaggle.com/rejpalcz/best-loss-function-for-f1-score-metric | |
- https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html#sklearn.metrics.f1_score | |
- https://discuss.pytorch.org/t/calculating-precision-recall-and-f1-score-in-case-of-multi-label-classification/28265/6 | |
''' | |
assert y_true.ndim == 1 | |
assert y_pred.ndim == 1 or y_pred.ndim == 2 | |
if y_pred.ndim == 2: | |
y_pred = y_pred.argmax(dim=1) | |
tp = (y_true * y_pred).sum().to(torch.float32) | |
tn = ((1 - y_true) * (1 - y_pred)).sum().to(torch.float32) | |
fp = ((1 - y_true) * y_pred).sum().to(torch.float32) | |
fn = (y_true * (1 - y_pred)).sum().to(torch.float32) | |
epsilon = 1e-7 | |
precision = tp / (tp + fp + epsilon) | |
recall = tp / (tp + fn + epsilon) | |
f1 = 2* (precision*recall) / (precision + recall + epsilon) | |
f1.requires_grad = is_training | |
return f1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
f1_score.py
def f1_loss(y_true:Fackel. Tensor, y_pred:Fackel. Tensor, is_training=False) -> torch. Tensor:
''''Berechnen F1-Score. Kann mit gpu Tensoren arbeiten
Die ursprüngliche Implmentation wurde von Michal Haltuf auf Kaggle geschrieben.
Gibt
-------
Fackel. Tensor
'ndim' == 1. 0 <= val <= 1
Verweis
---------
- https://www.kaggle.com/rejpalcz/best-loss-function-for-f1-score-metric
- https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html#sklearn.metrics.f1_score
- https://discuss.pytorch.org/t/calculating-precision-recall-and-f1-score-in-case-of-multi-label-classification/28265/6