PyTorch Connectomics documentation¶
This package is under development and should not be considered as formally released.
The field of connectomics aims to reconstruct the wiring diagram of the brain by mapping the neural connections at the level of individual synapses. Recent advances in electronic microscopy (EM) have enabled the collection of a large number of image stacks at nanometer resolution, but the annotation requires expertise and is super time-consuming.
PyTorch Connectomics consists of various deep learning based object detection, semantic segmentation and instance segmentation methods for the annotation and analysis of 3D image stacks. In addition, it consists of an easy-to-use data augmentation interface, tutorials on several common benchmark datasets, and helpful image stack processing functions, both for reproducing state-of-the-art results on benchmark datasets, and labelling large-scale volumes.