HID

HID Tutorial

This is the official support for competition of Human Identification at a Distance (HID). We report our result of 68.7% using the baseline model and 80.0% with re-ranking. In order for participants to better start the first step, we provide a tutorial on how to use OpenGait for HID.

Preprocess the dataset

Download the raw dataset from the official link. You will get three compressed files, i.e. train.tar, HID2022_test_gallery.zip and HID2022_test_probe.zip. After unpacking these three files, run this command:

python misc/HID/pretreatment_HID.py --input_train_path="train" --input_gallery_path="HID2022_test_gallery" --input_probe_path="HID2022_test_probe" --output_path="HID-128-pkl" 

Train the dataset

Modify the dataset_root in ./misc/HID/baseline_hid.yaml, and then run this command:

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 opengait/main.py --cfgs ./misc/HID/baseline_hid.yaml --phase train

You can also download the trained model and place it in output after unzipping.

Get the submission file

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 opengait/main.py --cfgs ./misc/HID/baseline_hid.yaml --phase test

The result will be generated in your working directory.

Submit the result

Follow the steps in the official submission guide, you need rename the file to submission.csv and compress it to a zip file. Finally, you can upload the zip file to the official submission link.