在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称:deep-object-reid开源软件地址:https://gitee.com/openvinotoolkit-prc/deep-object-reid开源软件介绍:Deep Object ReidDeep Object Reid is a library for deep-learning image classification and object re-identification, written in PyTorch.It is a part of OpenVINO™ Training Extensions. The project is based on Kaiyang Zhou's Torchreid project. Its features:
How-to instructions: https://github.com/openvinotoolkit/deep-object-reid/blob/ote/docs/user_guide.rst Original tech report by Kaiyang Zhou and Tao Xiang: https://arxiv.org/abs/1910.10093. You can find some other research projects that are built on top of Torchreid `here (https://github.com/KaiyangZhou/deep-person-reid/tree/master/projects). Also if you are planning to perform image classification project, please, refer to OpenVINO™ Training Extensions Custom Image Classification Templates to get a strong baseline for your project. The paper is comming soon. What's new
InstallationMake sure `conda (https://www.anaconda.com/distribution/) is installed. # cd to your preferred directory and clone this repogit clone https://github.com/openvinotoolkit/deep-object-reid.git# create environmentcd deep-object-reid/conda create --name torchreid python=3.7conda activate torchreid# install dependencies# make sure `which python` and `which pip` point to the correct pathpip install -r requirements.txt# install torchreid (don't need to re-build it if you modify the source code)python setup.py develop Get startedYou can use deep-object-reid in your project or use this repository to train proposed models or your own model through configuration file. Use deep-object-reid in your project
import torchreid
datamanager = torchreid.data.ImageDataManager( root='reid-data', sources='market1501', targets='market1501', height=256, width=128, batch_size_train=32, batch_size_test=100, transforms=['random_flip', 'random_crop'])
model = torchreid.models.build_model( name='osnet_ain_x1_0', num_classes=datamanager.num_train_pids, loss='am_softmax', pretrained=True)model = model.cuda()optimizer = torchreid.optim.build_optimizer( model, optim='adam', lr=0.001)scheduler = torchreid.optim.build_lr_scheduler( optimizer, lr_scheduler='single_step', stepsize=20)
engine = torchreid.engine.ImageAMSoftmaxEngine( datamanager, model, optimizer=optimizer, scheduler=scheduler, label_smooth=True)
engine.run( save_dir='log/osnet_ain', max_epoch=60, eval_freq=10, print_freq=10, test_only=False) Use deep-object-reid through configuration filemodify one of the following config file and run: python tools/main.py \--config-file $PATH_TO_CONFIG \--root $PATH_TO_DATA--gpu-num $NUM_GPU See "tools/main.py" and "scripts/default_config.py" for more details. EvaluationEvaluation is automatically performed at the end of training. To run the test again using the trained model, do python tools/eval.py \--config-file $PATH_TO_CONFIG\--root $PATH_TO_DATA \model.load_weights log/osnet_x1_0_market1501_softmax_cosinelr/model.pth.tar-250 \test.evaluate True Cross-domain settingSuppose you wanna train OSNet on DukeMTMC-reID and test its performance on Market1501, you can do python scripts/main.py \--config-file configs/im_osnet_x1_0_softmax_256x128_amsgrad.yaml \-s dukemtmcreid \-t market1501 \--root $PATH_TO_DATA Here we only test the cross-domain performance. However, if you also want to test the performance on the source dataset, i.e. DukeMTMC-reID, you can set: DatasetsImage-reid datasetsClassification dataset
ModelsClassification modelsReID-specific modelsFace Recognition specific modelsUseful links
CitationIf you find this code useful to your research, please cite the following papers. @article{torchreid, title={Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch}, author={Zhou, Kaiyang and Xiang, Tao}, journal={arXiv preprint arXiv:1910.10093}, year={2019}}@inproceedings{zhou2019osnet, title={Omni-Scale Feature Learning for Person Re-Identification}, author={Zhou, Kaiyang and Yang, Yongxin and Cavallaro, Andrea and Xiang, Tao}, booktitle={ICCV}, year={2019}}@article{zhou2019learning, title={Learning Generalisable Omni-Scale Representations for Person Re-Identification}, author={Zhou, Kaiyang and Yang, Yongxin and Cavallaro, Andrea and Xiang, Tao}, journal={arXiv preprint arXiv:1910.06827}, year={2019}} |
请发表评论