Metadata-Version: 2.4
Name: AdvSegLearn
Version: 0.1.0
Summary: Package for combining traditional and adversarial learning.
Author-email: Anthony Lino <aml334@case.edu>
License-Expression: MIT
Project-URL: Homepage, https://github.com/yourusername/
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-image
Requires-Dist: torchvision
Requires-Dist: matplotlib
Requires-Dist: opencv-python
Requires-Dist: Pillow
Dynamic: license-file

# AdvSegLearn
## Descriptor
 This package creates an easy to use api for training models on small datasets with adversarial learning.
 Important classes are:
 * Mutliclass_dataset - allows for both paired and unpaired images to be loaded, with built in support for initalized data augmentation and lazy loading data augmentation.
 * train_GAN - provides api to easily load in different models, datasets and loss functions to the model. Subclassing allows for easy modification of the training loop.
 * semi_supervised_loss - a loss function for the semisupervised training loop.
 * adversarial_loss - a loss function for hte unsupervised training loop.

# License
Probably the MIT License
