https://github.com/balditommaso/pylandscape
This project propose the loss landscape analysis as effective methodology to understand the robustness against natural perturbation of QNN.
https://github.com/balditommaso/pylandscape
loss-functions quantization-aware-training regularization-methods robustness
Last synced: 24 days ago
JSON representation
This project propose the loss landscape analysis as effective methodology to understand the robustness against natural perturbation of QNN.
- Host: GitHub
- URL: https://github.com/balditommaso/pylandscape
- Owner: balditommaso
- License: mit
- Created: 2025-02-02T16:10:37.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2026-03-26T10:53:56.000Z (about 1 month ago)
- Last Synced: 2026-03-26T13:35:56.368Z (about 1 month ago)
- Topics: loss-functions, quantization-aware-training, regularization-methods, robustness
- Language: Python
- Homepage: http://arxiv.org/abs/2502.08355
- Size: 32.8 MB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# PyLandscape
## Introduction
`pylandscape` is a Pytorch library for loss landscape analysis of neural networks. The library enables computing the following metrics:
- [CKA similarity](https://arxiv.org/pdf/2010.15327)
- [Hessian metrics](https://arxiv.org/pdf/1912.07145)
- [Mode connectivity](https://arxiv.org/pdf/1802.10026)
- [Loss surface](https://arxiv.org/pdf/1712.09913)
*NOTE*: All the functionalities relative to the computation of the Hessian metrics have been embedded via [PyHessian](https://github.com/amirgholami/PyHessian). If your interested in learning more about how these metrics are computed have a look to their Repository.
## Usage
### Install from Pip
You can install the library from pip:
```
pip install pylandscape
```