Tau
Tau
> Hi @liamsun2019, I think the large loss value may be caused by the abnormal value of sigma. You can try adding a bigger eps to sigma (e.g. 1e-5) to...
Hi, @Jeff-sjtu Since you follow the classification version of HRnet, the output dim of the first branch of HRNetw48 is 48, so after GlobalAvgPooling you pass a (B, 48) shaped...
Do you plan to use this page as an alternative of current algorithm docs? I suggest adding it into the docs instead of placing under the config folder. Besides, maybe...
> > Do you plan to use this page as an alternative of current algorithm docs? I suggest adding it into the docs instead of placing under the config folder....
从训练log来看结果是正常的，可能因为你没有使用基于imagenet的backbone预训练权重
Hi, it seems that your `batch_size` is too small than ours.
Thanks for your contribution! You can upload ckpts and logs(the json file) to an online driver like google, onedriver, etc. I'll save it to our server and return your a...
BTW, it seems that your PR branch is checkout from the main branch, which lags behind the `dev-1.x`. Would you mind rebasing it from `dev-1.x` following [our docs](https://mmpose.readthedocs.io/en/1.x/contribution_guide.html#create-a-development-branch)?
There is one thing that I'm concerned. The models you trained only used the RTMPose model architecture, but did not use the training strategy and data augmentation of RTMPose. These...
> oops, thanks for your feedback. I'll double check again on rtmpose-m. It seems that the `rtmpose-m` you trained is suboptimal, the performance of which is even worse than rtmpose-s.