You are here: Artificial Intelligence > Custom Deep Model Architectures

Custom Deep Model Architectures

Dragonfly's Custom Deep Model Architectures module supports deep learning models that have a different architecture than the ones supported in the Deep Learning Tool. The current models implemented in the module include YOLOv3 for object detection. Additional models that will be implemented in future versions include Cellpose for cellular segmentation and StarDist, a cell/nuclei detection method for microscopy images with star-convex shape priors.

 

Dragonfly Help Live Version