search

Gait3D / Gait3D-Benchmark

This is the code for the paper "Gait Recognition in the Wild with Dense 3D Representations and A Benchmark. (CVPR 2022)", "Gait Recognition in the Wild with Multi-hop Temporal Switch", and "Parsing is All You Need for Accurate Gait Recognition in the Wild".
133 stars 19 forks source link

config #23

Closed Lxzzzzzzzzzzz closed 5 months ago

Lxzzzzzzzzzzz commented 5 months ago

what is the different between smplgait.yaml and smplgait_gait3d.yaml?why need two?

JinkaiZheng commented 5 months ago

Hi~ Thank you for your inquiry. The "smplgait.yaml" is the configuration file replicated by the OpenGait Team, while the "smplgait_gait3d.yaml" is the configuration used in our original research paper.

Lxzzzzzzzzzzz commented 5 months ago

Thank you for your reply! I also want to know if i want to recurrent the result in your original research paper result , should i just change data_in_use: [false, true, true] to [true, true] in the smplgait_gait3d.yaml?

JinkaiZheng commented 5 months ago

You can use smplgait_gait3d.yaml directly without modifying any configuration.

Lxzzzzzzzzzzz commented 5 months ago

Thank you for your reply! But i just use "python datasets/Gait3D/merge_two_modality.py --sils_path 'Gait3D-sils-64-64-pkl' --smpls_path 'Gait3D-smpls-pkl' --output_path 'Gait3D-merged-pkl' --link 'hard' " instead of " python datasets/Gait3D/merge_three_modality.py --pars_path 'Gait3D-pars-64-64-pkl' --sils_path 'Gait3D-sils-64-64-pkl' --smpls_path 'Gait3D-smpls-pkl' --output_path 'Gait3D-merged-pkl' --link 'hard' ". So if i want to recurrent the result in your original research paper result , should i just change data_in_use: [false, true, true] to [true, true] in the smplgait_gait3d.yaml?

JinkaiZheng commented 5 months ago

Yes