Hello! How may I assist you today?

Human Identification at a Distance (HID) Competition This is the official support for Human Identification at a Distance (HID) competition. We provide the baseline code for this competition. ## Tutorial for HID 2023 For HID 2023, we will not provide a training set. In this competition, you can use any dataset, such as CASIA-B, OUMVLP, CASIA-E, and/or their own dataset, to train your model. For the HID 2023 competition, there will not be a provided training set. Participants can use any dataset, such as CASIA-B, OUMVLP, CASIA-E, and/or their own dataset, to train their model. However, for the HID 2022 competition, you can download the raw dataset from the official link and use the 'pretreatment_HID.py' script to preprocess the data for training. In this tutorial, we will use the model trained on previous HID competition training set as the baseline model. ### Download the test set Download the test gallery and probe from the link. You should decompress these two file by following command: mkdir hid_2023 tar -zxvf gallery.tar.gz mv gallery/* hid_2023/ rm gallery -rf # For Phase 1 tar -zxvf probe_phase1.tar.gz -C hid_2023 mv hid_2023/probe_phase1 hid_2023/probe # For Phase 2 tar -zxvf probe_phase2.tar.gz -C hid_2023 mv hid_2023/probe_phase2 hid_2023/probe ### Download the pretrained model Download the pretrained model and place it in 'output' after unzipping. wget https://github.com/ShiqiYu/OpenGait/releases/download/v1.1/pretrained_hid_model.zip unzip pretrained_hid_model.zip -d output/ ## Generate the result Modify the 'dataset_root' in 'configs/baseline/baseline_hid.yaml', and then run this command: shell CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 opengait/main.py --cfgs configs/baseline/baseline_hid.yaml --phase test The result will be generated in 'HID_result/current_time.csv'. ## Submit the result Rename the csv file to 'submission.csv', then zip it and upload to official submission link. Normally, you should get a score of 48.3 in phase 1. --- ## (Deprecated) Tutorial for HID 2022 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: shell python datasets/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 'configs/baseline/baseline_hid.yaml', and then run this command: shell CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 opengait/main.py --cfgs configs/baseline/baseline_hid.yaml --phase train You can also download the trained model and place it in 'output' after unzipping. ### Get the submission file shell CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 opengait/main.py --cfgs configs/baseline/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.

Hello! This seems to be a tutorial for the Human Identification at a Distance (HID) competition. How can I assist you with this? 对 Sorry, I didn't understand your response. Could you please rephrase or provide more information on how I can assist you with the HID competition tutorial?