lunalulu

When I trained this network with the person data set(trian data number 2785,test data number 310) I collected myself, the loss function converges slowly and the test accuracy is not...

network prepare?

3

Is there no padding in the preprocessing of the network input?

please tell me the version of pytorch?

about pose_NMS error

1

I think the description of pose_NMS in the paper is wrong, d(Pi, Pj|Λ, λ) ≤ η should be d(Pi, Pj|Λ, λ) > η??? The code seems to support my idea,...

i want to know the accuracy of the pretrained models resnet18 and resnet50? thanks

When parsing the network output, why are the width and height of key points calculated as follows: ` output[:, :, :, 4:96:6] = output[:, :, :, 4:96:6].pow(2) * cfg.IMG_SIZE output[:,...

Something i don't understand?

3

thanks for your wonderful jobs~ I have some questions that I don't understand. I hope you can help me answer them. 1、src/demo.py line26-31, I don't know why I'm doing this...

problem about sppe GT generate?

3

thanks for your great work!  i read the code about sppe GT heatmaps generating, the code above. I don't think that's consistent with the calculation of loss in the...

about oneposeCap app?

1

I collect an annotated or test data by following the app's instruction， but often get stuck, there is no download link after stopping. Occasionally, the download link can pop up,...