Giters

TiagoCortinhal / SalsaNext

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

acc on the nuscenes mini dataset

ZT-AIA opened this issue · comments

commented

Hi, due to arithmetic limitations I am only training and validating on the nuscenes mini dataset, trained 3 times each 400 rounds the acc is 44.3%, 46.9%, 45.1% respectively, is this a normal level, have you done the same here?