mAP on VOC07

[moothes]

I train the source code on 07train+12train sets of PASCAL VOC, and test on 07test set. The mAP is 66.13. Training loss is around 1 while test loss between 2-5. The batch size is set to 11 due to the limitation of our GPU. Other settings are the same as in COCO. I miss something? Anyone has better results?

[moothes]

Moreover, I use the FPN as backbone and achieve 63.25 mAP on 07test set.

[xingyizhou]

I tried fine-tuning the provided CornerNet_500000 on VOC with two GPU for one day, it gives around 81 mAP. Training from scratch on 2 GPUs for one week (250k iters) on VOC gives about 70 mAP according to my preliminary experiments.

[oujieww]

I think the reason should be pretrain-weights? for ssd,fssd,rfbssd, they used imagenet pretrained vgg as init weights,but for hourglass-model, there are not pretrained weights.coco dataset is big enough,but voc dataset is not as big as coco

[Xudangliatiger]

。。so the paper did not try voc07, guess that voc is not big enough to train from scratch

[TEOEFW]

How can i train cornetNet in on VOC data?

[Complicateddd]

I train the source code on 07train+12train sets of PASCAL VOC, and test on 07test set. The mAP is 66.13. Training loss is around 1 while test loss between 2-5. The batch size is set to 11 due to the limitation of our GPU. Other settings are the same as in COCO. I miss something? Anyone has better results? can u tell me how to modify the code to test voc dataset on a train model in voc

[Glutton-zh]

i train on voc2007 too but i just get a rusult.json but map, how can i get the map about my model