DeepFaune New England
March 18, 2025
This repository contains code for training and running the DeepFaune New England (DFNE) model for species classification in trail camera imagery. This model is a re-trained version of the DeepFaune model for classifying European species in trial cameras, fine-tuned to classify
taxa from northeastern North America. The DFNE model takes as input cropped images of each animal, which can be generated by an object detection model. DFNE classifies 24 taxa, including the "no-species" label indicating the absence of an animal. The code structure for running DFNE was inspired by Pytorch-Wildlife (PW), allowing for easy integration of PW features for localizing and cropping animals in images and for post processing of model outputs.
taxa from northeastern North America. The DFNE model takes as input cropped images of each animal, which can be generated by an object detection model. DFNE classifies 24 taxa, including the "no-species" label indicating the absence of an animal. The code structure for running DFNE was inspired by Pytorch-Wildlife (PW), allowing for easy integration of PW features for localizing and cropping animals in images and for post processing of model outputs.
Citation Information
| Publication Year | 2025 |
|---|---|
| Title | DeepFaune New England |
| DOI | 10.5066/P13T4EKE |
| Authors | Therese M Donovan, Laurence A Clarfeld, Katherina Geider, Angela K Fuller |
| Product Type | Software Release |
| Record Source | USGS Asset Identifier Service (AIS) |
| USGS Organization | Cooperative Research Units Program |
| Rights | This work is marked with CC0 1.0 Universal |