Datasets for "uncovering developmental time and tempo using deep learning"

Abstract: This is the data repository for training and testing the Twin Network. The imaging data repositories are divided into several packages based on independent experiments. The data comprises bright-field time-lapse images of zebrafish embryos acquired in multiple batches within multi-well plates using an Acquifer Imaging Machine. Individual embryo segments were identified and extracted using a trained neural network for object detection. Within these experiment folders, data are organized by microscope position and embryo number.