Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection icon indicating copy to clipboard operation
Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection copied to clipboard

Published 20 hours ago • verified publisher icon hdjang

The result of FSAF model (mAP) is lower than expected.

Open icennaise opened this issue 5 years ago • 0 comments
trafficstars

I train the FSAF and RetinaNet model respectively with default config on single PC, but get a strange result which the mAP of RetinaNet is 28.7% and that of FSAF is 27.0%, but according to your paper, the mAP of FSAF might be 0.2% higher than RetinaNet model.

I train model like that: python tools/train.py configs/retinanet_r50_400_050x.py python tools/train.py configs/fsaf_r50_400_050x.py

run on unbuntu 18.04 python 3.7 Pillow version is 6.1.0 pytorch version is 1.1.0

icennaise avatar Apr 14 '20 06:04 icennaise