Yining Li

Here we don't have a specific metric for selecting the pretrained model. Usually, we simply compare the visualized results after each epoch and choose the visually best one. We observed...

This is probably caused by the BN layer in the model. BN layers will track running statistics (mean and variance) in testing, so using a different batch_size from training setting...

Thank you very much for your contribution. It's inspiring to receive feedback on the newly released 1.0 version. We have enabled the readthedocs pages for the 1.x branch so '1.x'...

Hi, thanks for this PR. We will close it for now and feel free to contact us if there are any other questions.

MMPose will automatically download the checkpoint to a temporal folder at the first time it is used in inference. Are you face any problems at this step?

It looks like the download link can not be accessed from your virtual server. Is it possible to manually upload the checkpoint to your server?

Is this PR working in progress or ready to merge?

#1638 has been merged. Please rebase the pr branch onto the latest dev-1.x

> 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,...

Dataset visualization will be supported soon. For now you may need to build data samples from the dataset annotation and manually call the `show_result` function of the model.