Jake Graving

Hmmm... I guess the easiest thing to do would be to have separate Flipud and Fliplr augmenters that subclass the imgaug version. I'd welcome a PR if you want to...

> but it seems that the Flipud and Fliplr augmenters already have the functionality you'd want them to have They flip the keypoint locations, but not the labels/ordering of the...

What image resolution are you using? Both dimensions should be divisible by 2 multiple times. Also I notice you seem to be using a 3d dataset from DeepLabCut, so I'm...

Yes there may be a bug with the graph drawing functionality. Will have to look into it further

Hi, Thanks for your interest. We don't have any pretrained human model at the moment, but we have had several people request this and will likely add one in a...

Hi, currently the API only supports predicting on images that are the same size as the training images, but this will be changed in a coming update. However, this is...

Hi, I'm not sure exactly what you mean, but currently all of the images in the training set must be the same size.

Thanks for sharing. Looks like a very cool approach. Solves a lot of the complexity with multiple pose estimation we discussed in the paper. We don't have any concrete plans...

Currently there is no way to indicate that body part is not visible when making annotations. We're still testing this feature internally (ended up being a bit more complicated than...

We had a student working on this as part of a larger update, who unfortunately left before they finished the update. This ended up being more complicated than I originally...