Julieta Martinez

Mmm. Yeah let’s wait for Javier’s answer. On Sat, Oct 20, 2018 at 11:29 PM Coder_Hong wrote: > http://humaneva.is.tue.mpg.de/ > > — > You are receiving this because you commented....

Could you please elaborate? How are they wrong?

Please give TF 1.2 a try: https://github.com/una-dinosauria/3d-pose-baseline/issues/197#issuecomment-904477938

Not in particular. The data you are testing on may have a somewhat different viewing angle than the one you trained on.

1. Sorry, when you say that "it starts at 63.95", are you referring to the Average error in the validation set? 2. What OS and TF version do you have?

I think you forgot to add `--procrustes` to the last command. I am getting 63.8 in the first epoch and I can confirm that the error is increasing. I'll investigate...

Hi @matteorr, I ran these through my colleagues and @rayat137 noticed that, when you call ```python _, test_set_2d, _, _, _, _ = data_utils.read_2d_predictions(actions, FLAGS.data_dir) ``` The 2d test set...

Hi @matteorr, Please note that the functions `data_utils.create_2d_data` and `data_utils.read_2d_predictions` return the data already normalized -- I should've probably chosen better names for them. So with the changes that you...

Hi @matteorr, I tried to reproduce the GT/SH values myself, and I've realized that this is far from trivial for someone not familiar with the codebase. I've added the commit...

Hi @matteorr, > * Is there a reason you're using the fine-tuned SH detections, and do you remember if those are the ones you used in Table 1? When trying...