search

facebookresearch / AGRoL

Code release for "Avatars Grow Legs Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model", CVPR 2023
Other
239 stars 24 forks source link

Questions about overlapping test and real-time prediction #14

Open cccvision opened 1 year ago

cccvision commented 1 year ago

hi authors, I have some questions about the overlapping test, thanks in advance for your help!

  1. Can this work really run in real-time? In the paper, it is written that ' AGRoL model achieves real-time inference speed' because it 'produces 196 output frames in 35 ms'. However, for online prediction, given one new observation, we only need one prediction (like what AvatarPoser did), 196 outputs seem redundant, how do you make it work for real-time usage?

  2. when I tried to test with overlapping, It shows the following errors: python test.py --model_path /path/to/your/model --timestep_respacing ddim5 --support_dir /path/to/your/smpls/dmpls --dataset_path ./dataset/AMASS/ --overlapping_test

Loading dataset... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 536/536 [00:00<00:00, 1072.94it/s] Creating model and diffusion... Loading checkpoints from [pretrained_weights/diffmlp.pt]... Overlapping testing... 0%| | 0/536 [00:00<?, ?it/s] Traceback (most recent call last): File "test.py", line 552, in main() File "test.py", line 516, in main output, body_param, head_motion, filename = test_func( File "test.py", line 269, in overlapping_test memory_end_index = sparse_splits[step_index][1] IndexError: index 1 is out of bounds for dimension 0 with size 1

asanakoy commented 1 year ago

Hey. Even if you run prediction with a sliding window of stride 1, then it will require 35 ms per every prediction. Which is ~30 FPS