Mathis Petrovich

As ``fid_l`` and ``fid_r`` are used before (line 164) and after shifting the indexes (line 182), one or the other should be wrong I think.

> I didn't find the one used earlier, are you referring to line 163 comments? I was refering to line 166 https://github.com/anindita127/Complextext2animation/blob/d89730c17580c5b9ccb767d55257f6781eec062a/src/data.py#L166 Then, the shifting on indexes in line 177...

Hi, When you are evaluating your method against the ground truth motion, which text sequence do you use? (if there are several available for a particular sequence) As your output...

Ok thanks, to be sure I get it, given a motion M1 with the annotations A1/B1/C1, M2 with the annotations A2/B2, you will create (M1/A1), (M1/B1), (M1/C1), (M2/A2) and (M2/B2)?...

Thanks it is much clear now. I have another question about the number of data for the test set. When I sample the sequences with the command: ```bash python sample_wordConditioned.py...

Hi, I update the README.md. You can use the command line: ``bash prepare/download_previous_works.sh`` to download the motion generated from previous work. Then ``python evaluate.py folder=previous_work/ghosh`` to evaluate on ghosh et...

Hello all, Sorry for the delay, I don't have a Windows machine so I cannot reproduce the error myself. Did anyone succeed at the end?