tusen-ai/SST

error in performanece of fsdv2

Open

#137 aberto em 21 de ago. de 2023

Ver no GitHub
 (17 comments) (0 reactions) (0 assignees)Python (106 forks)github user discovery
good first issue

Métricas do repositório

Stars
 (883 stars)
Métricas de merge de PR
 (Métricas PR pendentes)

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

Guia do colaborador