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

GREW pretreatment `to_pickle` has size 0 #6

Closed gosiqueira closed 2 years ago

gosiqueira commented 2 years ago

I'm trying to run GREW pretreatment code but it generates no GREW-pkl folder at the end of the process. I debugged myself and checked if the --dataset flag is set properly and the to_pickle list size before saving the pickle file. The flag is well set but the size of the list is always 0.

I downloaded the GREW dataset from the link you guys sent me and made de GREW-rearranged folder using the code provided. I'll keep investigating what is causing such an error and if I find I'll set a fixing PR.

JinkaiZheng commented 2 years ago

Hi~ I guess you are using the newer OpneGait code. If you want to run GREW successfully, you have two options: 1) Please download the source code for this repo and run sh misc/run_pretreatment_grew.sh with the original directory structure that GREW decompressed. Then, please refer to the train /test file and rewrite the command as follows: For training: CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 lib/main.py --cfgs ./config/gaitset_64pixel_GREW_office_split.yaml --phase train For testing: CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 lib/main.py --cfgs ./config/gaitset_64pixel_GREW_office_split.yaml --phase test In addition, you can change the config file to gaitset_64pixel_GREW_our_split.yaml to implement localization testing, as used in our paper. 2) Download the latest OpneGait source code and follow their tutorial.