Any one test the accuracy on VOC dataset?

Question

Any one test the accuracy on VOC dataset?

blueardour opened this issue 6 years ago · 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?

Answer 1 · 2018-12-24T11:31:19.000Z

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

Answer 2 · 2018-12-24T11:36:46.000Z

also my ssd_lite_mobilenetv2_voc is just 0.66

Answer 3 · 2018-12-25T00:49:39.000Z

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

Answer 4 · 2018-12-25T01:24:47.000Z

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?

Answer 5 · 2018-12-26T01:19:50.000Z

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

Answer 6 · 2018-12-27T02:41:02.000Z

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

Answer 7 · 2019-03-31T12:36:38.000Z

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

do you slove?