Question about the Result

[Hiroy101]

I tried to use VOC dataset, so i have modified the dataloader and the evaluation code with some parts of mmedetction. However, i got really pool result (mAP is about 0.167) after 17 epochs training（about 1 day）. So, i'm wondering how many epochs did your coco dataset cost, and what's your final AP result? I would be very grateful if you could give me the answer.

[deepaksinghcv]

Hello @Hiroy101 , Did you get any better results. I'm able to reproduce around 19-20 mAP on PASCAL VOC validation

[Hiroy101]

@deepakksingh, finally i switched to other frameworks cause i did not get any better result since then.

[deepaksinghcv]

@Hiroy101 Thanks for your quick reply. I'm able to reproduce results using mmdetection and Detectron2.
BTW, were you able to train using resnet50_fpn backbone in this repo ?
It throws RuntimeError: shape '[387072, -1]' is invalid for input of size 1571328 when i try to change the backbone to resnet50_fpn.

[Hiroy101]

@deepakksingh, I seem to have encountered a similar problem at that time, it should be because the size of the FPN output feature map does not match the subsequent input, maybe you can try to modify it. this is all the help i can give u, sorry. i cant remember other specific details -_-||

[deepaksinghcv]

Thanks @Hiroy101, I will check it.