Skip to content

Latest commit

 

History

History
46 lines (26 loc) · 1.24 KB

File metadata and controls

46 lines (26 loc) · 1.24 KB

Human Motion Infilling(Pytorch)


Result:


Usage:

Data

  1. Get data from Holden et al
  2. Pre-pocessing by using code from Kaufmann et al

Run on the code:

Training

python train.py --name <name_of_experiment> --datasetPath <your_train_data_path> --ValdatasetPath <your_valid/test_data_path> 

The results will save in <Code_path>/experiments(default)/

You can check the default setting and use it from line 25 to 34 <Code_path>/train.py

Visualization

The visualization codes are referd from Here

cd <Code_path>/VisualizationCode ; python view.py --name <name_of_experiment> --epoch <num of epoch(train)>

Reference

Reference Paper(3DV 2020)

Official Github (Tensorflow) of reference paper