-
Notifications
You must be signed in to change notification settings - Fork 0
This repository includes the code and data presented in the paper "Confronting Domain Shift in Trained Neural Networks". In NeurIPS 2020 Workshop on Pre-registration in Machine Learning (pp. 176-192). PMLR.
License
sandialabs/confronting_domain_shift
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
This repository includes the code and data presented in the paper, "Confronting Domain Shift in Trained Neural Networks", Martinez, C., Najera-Flores, D. A., Brink, A. R., Quinn, D. D., Chatzi, E., & Forrest, S. (2021, July). Confronting Domain Shift in Trained Neural Networks. In NeurIPS 2020 Workshop on Pre-registration in Machine Learning (pp. 176-192). PMLR. The code was tested with Python 3.6.8 and dependencies (found in requirements.txt) were installed with pip 21.0.1. Model and data configurations should be set with config files in .json format. An example config file is found here: configs/example_train.json To train a model: python train.py configs/example_train.json To run inference: python infer.py configs/example_infer.json Data used in the experiments for the paper are located in the ./data directory. SAND2021-15138O
About
This repository includes the code and data presented in the paper "Confronting Domain Shift in Trained Neural Networks". In NeurIPS 2020 Workshop on Pre-registration in Machine Learning (pp. 176-192). PMLR.
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published