Open Source

Introducing SAHI, our open source Computer Vision Library, designed to elevate object detection and instance segmentation capabilities. Unlike similar applications, SAHI employs advanced technologies, allowing for more detailed analysis and extraction. In the realm of computer vision, where limitations persist, SAHI stands out by enabling end-to-end identification of even the smallest objects in large-scale images. This application excels in detecting objects and improves prior research and scales up the utilization in the industry. Notably, the latest version offers easy installation via the Python package management system, “pip.” With over 1 million worldwide downloads and 2k stars on Github, SAHI has proven indispensable for users globally. Explore the project further on our Github page: https://github.com/obss/sahi

Trapper is an NLP library that aims to make it easier to train transformer based models on downstream tasks. It provides a dependency-injection mechanism and allows defining training and/or evaluation experiments via configuration files. By this way, you can replicate your experiment with different models, optimizers etc by only changing their values inside the configuration file without writing any new code or changing the existing code. These features foster code reuse, less boiler-plate code, as well as repeatable and better documented training experiments which is crucial in machine learning. Explore the project further on our Github page: https://github.com/obss/trapper

A package for processing signals recorded using wearable sensors, such as Electrocardiogram (ECG), Photoplethysmogram (PPG), Electrodermal activity (EDA) and 3-axis acceleration (ACC).

BIOBSS’s main focus is to generate end-to-end pipelines by adding required processes from BIOBSS or other Python packages. Some preprocessing methods were not implemented from scratch but imported from the existing packages. Explore the project further on our Github page: https://github.com/obss/biobss