Models for paper "From crowd to herd counting: How to precisely detect and count African mammals using aerial imagery and deep learning?"
Domaine:
geospatialagriculture
Type de record:
model
Créateur:
DelFouThéBus
Éditeur:
Del
Éditeur:
ULi
Hôte:
HerdNet architecture parameters (stored in '.pth' files), trained separately on : nadir aerial images, containing 6 African wildlife species, from the general dataset of Delplanque et al. (2022), oblique aerial images, containing 3 African livestock species, from the Ennedi dataset of Delplanque et al. (2023). These files have been obtained using the HerdNet code (v0.1.0), published on Github: Alexandre-Delplanque/HerdNet These pre-trained models follow the CC BY-NC-SA-4.0 license and are available for academic research purposes only, no commercial use is permitted.