torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Python

The article presents the torchosr package - a Python package compatible with PyTorch library - offering tools and methods dedicated to Open Set Recognition in Deep Neural Networks. The package offers two state-ofthe-art methods in the field, a set of functions for handling base sets and generation of derived sets for the Open Set Recognition task (where some classes are considered unknown and used only in the testing process) and additional tools to handle datasets and methods. The main goal of the package proposal is to simplify and promote the correct experimental evaluation, where experiments are carried out on a large number of derivative sets with various Openness and class-to-category assignments. The authors hope that state-of-the-art methods available in the package will become a source of a correct and open-source implementation of the relevant solutions in the domain. Methods to solve this task are exceedingly demanded in the face of the growing popularity of deep neural networks, whose distinctive feature is unsupervised feature extraction [3]. This task is not trivial both in the context of method proposals and evaluation. Samples of known classes (KKC) are present both in the process of training and testing the model. One of the criteria for evaluating OSR methods is the correct classification within these classes. Unknown class samples (UUC), on the other hand, are used only in the process of testing methods [2]. The task of the algorithms is to mark these samples as instances of unknown classes.