Spaces:
Runtime error
Runtime error
Commit
·
1784bf6
1
Parent(s):
8e2260e
Update Readme
Browse files
README.md
CHANGED
|
@@ -10,7 +10,6 @@ pinned: true
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
-
<<<<<<< HEAD
|
| 14 |
# OOD Detection Demo
|
| 15 |
|
| 16 |
Out-of-distribution (OOD) detection is an essential safety measure for machine learning models. This app demonstrates how these methods can be useful in determining wether the inputs of a ResNet-50 model trained on ImageNet-1K can be trusted by the model.
|
|
@@ -38,6 +37,3 @@ python app.py
|
|
| 38 |
- [ ] [Mahalanobis Distance](https://arxiv.org/abs/1807.03888)
|
| 39 |
- [x] [Maximum Softmax Probability](https://arxiv.org/abs/1610.02136)
|
| 40 |
- [x] [Energy Based Out-of-Distribution Detection](https://arxiv.org/abs/2010.03759)
|
| 41 |
-
=======
|
| 42 |
-
# OOD Detection
|
| 43 |
-
>>>>>>> 45fabfa417588e2aeb366695552bd6c8de1e73cc
|
|
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
|
|
|
| 13 |
# OOD Detection Demo
|
| 14 |
|
| 15 |
Out-of-distribution (OOD) detection is an essential safety measure for machine learning models. This app demonstrates how these methods can be useful in determining wether the inputs of a ResNet-50 model trained on ImageNet-1K can be trusted by the model.
|
|
|
|
| 37 |
- [ ] [Mahalanobis Distance](https://arxiv.org/abs/1807.03888)
|
| 38 |
- [x] [Maximum Softmax Probability](https://arxiv.org/abs/1610.02136)
|
| 39 |
- [x] [Energy Based Out-of-Distribution Detection](https://arxiv.org/abs/2010.03759)
|
|
|
|
|
|
|
|
|