The Annotated Germs for Automated Recognition (AGAR) dataset is an image database of microbial colonies cultured on agar plates. It contains 18 000 photos of five different microorganisms as single or mixed cultures, taken under diverse lighting conditions with two different cameras. All the images are classified into countable, uncountable, and empty, with the countable class labeled by microbiologists with colony location and species identification (336 442 colonies in total). This study describes the dataset itself and the process of its development. In the second part, the performance of selected deep neural network architectures for object detection, namely Faster R-CNN and Cascade R-CNN, was evaluated on the AGAR dataset. The results confirmed the great potential of deep learning methods to automate the process of microbe localization and classification based on Petri dish photos. Moreover, AGAR is the first publicly available dataset of this kind and size and will facilitate the future development of machine learning models. The data used in these studies can be found at https://agar.neurosys.com/.

No abstract

We make use of two well-known numerical approaches of nonlinear pulse propagation, namely the unidirectional pulse propagation equation and the multimode generalized nonlinear Schrödinger equation, to provide a detailed comparison of ultrashort pulse propagation and possible conical emission in the context of multimode optical fibers. We confirm the strong impact of the frequency dispersion of the nonlinear response on pulse splitting and supercontinuum dynamics in the femtosecond regime for pumping powers around the critical self-focusing threshold. Our results also confirm that the modal distribution of optical fibers provides a discretization of conical emission of the corresponding bulk medium (i.e., here fused silica). This study also provides some criteria for the use of numerical models and it paves the way for future nonlinear experiments in commercially-available optical fibers.