Skip to content

Commit 9ac3483

Browse files
committed
readme updates
1 parent 32ba413 commit 9ac3483

File tree

2 files changed

+34
-8
lines changed

2 files changed

+34
-8
lines changed

README.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,8 @@
1-
# TorchDrift -- drift detection on PyTorch
1+
# TorchDrift: drift detection on PyTorch
22

3-
TorchDrift lets you monitor your PyTorch models to see if the data
4-
matches what it has been trained for. We focus on practical application
3+
TorchDrift is a data and concept drift library for PyTorch. It lets you monitor your PyTorch models to see if they operate within spec.
4+
5+
We focus on practical application
56
and strive to seamlessly integrate with PyTorch.
67

78
# Installation

docs/source/index.rst

Lines changed: 30 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,10 @@
1-
Welcome to TorchDrift!
2-
======================
1+
TorchDrift: drift detection on PyTorch
2+
======================================
33

4-
TorchDrift is a PyTorch package for monitoring models and detecting drift.
4+
TorchDrift is a data and concept drift library for PyTorch. It lets you monitor your PyTorch models to see if they operate within spec.
5+
6+
We focus on practical application
7+
and strive to seamlessly integrate with PyTorch.
58

69
.. toctree::
710
:maxdepth: 2
@@ -32,8 +35,30 @@ TorchDrift is a PyTorch package for monitoring models and detecting drift.
3235
reducers
3336
data_functional
3437
utils
35-
36-
38+
39+
40+
Authors
41+
=======
42+
43+
TorchDrift is a joint project of Orobix Srl, Bergamo, Italy and
44+
MathInf GmbH, Garching b. München, Germany.
45+
46+
The TorchDrift Team: Thomas Viehmann, Luca Antiga, Daniele Cortinovis, Lisa Lozza
47+
48+
Acknowledgements
49+
================
50+
51+
We were inspired by
52+
53+
- Failing Loudly: An Empirical Study of Methods for Detecting Dataset
54+
Shift, NeurIPS 2019
55+
https://github.com/steverab/failing-loudly
56+
- Hendrycks & Dietterich:
57+
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
58+
ICLR 2019
59+
https://github.com/hendrycks/robustness/
60+
- Van Looveren et al.: Alibi Detect https://github.com/SeldonIO/alibi-detect/
61+
3762

3863
Indices and tables
3964
==================

0 commit comments

Comments
 (0)