the influence of detector
msunming opened this issue · comments
the performance of human AP from the 57.2 to 62.9 increase extra 1% in human pose, will you release the result of 62.9 human detection result for analyze the importance of detector?
The influence of detection has been analyzed in minival dataset in paper. And now I don’t have the detection result. I’m sorry.
3Q. the conclusion may seems conflict in paper about the influence of detector. Besides , the nms thr is set one?
The detector has a greater but still limited impact on test-dev dataset which we found later. Soft-nms is applied in the given detection result.
the resnet50 var name seems not completely same as tf website, the weight is trained by youself or transform from tf?
sorry, its weight same with tf resnet50.
In the report, the batchsize also is important. Do you try implement BN cross-gpus and related experiment ?