tusen-ai/SST

error in performanece of fsdv2

Open

#137 opened on Aug 21, 2023

 (17 comments) (0 reactions) (0 assignees)Python (106 forks)github user discovery
good first issue

Repository metrics

Stars
 (884 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

I tried to train fsdv2 on waymo perception V1_4_0,and get the performance on validation set as follows. which is much lower than the performance in the paper

OBJECT_TYPE_TYPE_VEHICLE_LEVEL_1: [mAP 0.749648] [mAPH 0.745259] OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2: [mAP 0.669701] [mAPH 0.66562] OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_1: [mAP 0.80301] [mAPH 0.755212] OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2: [mAP 0.73128] [mAPH 0.685319] OBJECT_TYPE_TYPE_SIGN_LEVEL_1: [mAP 0] [mAPH 0] OBJECT_TYPE_TYPE_SIGN_LEVEL_2: [mAP 0] [mAPH 0] OBJECT_TYPE_TYPE_CYCLIST_LEVEL_1: [mAP 0.744445] [mAPH 0.734285] OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2: [mAP 0.719278] [mAPH 0.709439]

image

This is the config I used fsdv2_waymo_full_2x.txt

Contributor guide