ShuangXieIrene/ssds.pytorch

Any one test the accuracy on VOC dataset?

blueardour opened this issue · 7 comments

Hi, everyone,
I test the pre-trained model on the VOC dataset, and found the mAP didn't match the expected ones.
Here is my result:
yolo_v2_mobilenetv2_voc: 0.721956
yolo_v3_mobilenetv2_voc: 0.766846
ssd_lite_mobilenetv2_voc: 0.708510
rfb_lite_mobilenetv2_voc: 0.713691
fssd_lite_mobilenetv2_voc: 0.744321
It can be seen, yolov2/3 perform better than the author's result, however the other three are bad than the expected result.

Have anyone met this problem?

Did you test the mAP of SSD+VGG+VOC ? Mine is just 0.47

also my ssd_lite_mobilenetv2_voc is just 0.66

I only focus on mobilenetv2. Which pytorch version and python version do you employ?

Python 3.5 torch 3.1 When I tried the other SSD net,it is right.So the version I think is doesn`t matter.Did you used the pretraining model?

Yes, pre-trained model was used. My environment is python2.7/3.6 and pytorch 0.4.1

Could you tell me the learning rate and max epoch of yours ? Thanks a lot!

Could you tell me the learning rate and max epoch of yours ? Thanks a lot!

do you slove?