Meta tags:
description=OpenSphere is an easy-to-use hyperspherical face recognition library based on PyTorch.;

Headings (most frequently used words):

hyperspherical, face, recognition, opensphere, is, an, easy, to, use, library, based, on, pytorch, brief, history, of, getting, started, citation,

Text of the page (most frequently used words):
and (20), the (10), face (8), #recognition (8), hyperspherical (6), config (6), train (6), #opensphere (6), for (5), title (4), author (4), liu (4), weiyang (4), wen (4), yandong (4), year (4), yml (4), loss (3), booktitle (3), sphereface (3), raj (3), bhiksha (3), framework (3), github (3), cuda_visible_devices (3), python (3), test (3), model (3), inproceedings (2), zhiding (2), deep (2), article (2), sphereface2 (2), weller (2), adrian (2), singh (2), rita (2), 2022 (2), research (2), download (2), environment (2), git (2), clone (2), easy (2), use (2), library (2), based (2), pytorch (2), liu2016lsoftmax, large, margin, softmax, convolutional, neural, networks, yang, meng, icml, 2016, liu2017sphereface, hypersphere, embedding, ming, song, cvpr, 2017, wen2022sphereface2, binary, classification, all, you, need, iclr, liu2022spherefacer, revived, unifying, journal, ieee, transactions, pattern, analysis, machine, intelligence, this, helps, your, please, consider, cite, citation, see, our, detailed, instructions, page, ijbb, vggface2_sfnet20_sphereface, vggface2_sfnet20_sphereface2, bash, scripts, dataset_setup, dataset, conda, env, create, setup, opensphere_v0, single, branch, https, com, ydwen, repository, getting, started, brief, history, provides, consistent, unified, training, evaluation, decouples, function, from, other, varying, components, such, network, architecture, optimizer, data, augmentation, can, fairly, compare, different, functions, popular, benchmarks, serving, transparent, platform, reproduce, published, results, skip, content,

Text of the page (random words):
opensphere opensphere is an easy to use hyperspherical face recognition library based on pytorch skip to the content opensphere is an easy to use hyperspherical face recognition library based on pytorch github download opensphere provides a consistent and unified training and evaluation framework for hyperspherical face recognition research the framework decouples the loss function from the other varying components such as network architecture optimizer and data augmentation it can fairly compare different loss functions in hyperspherical face recognition on popular benchmarks serving as a transparent platform to reproduce published results brief history of hyperspherical face recognition getting started clone the repository git clone b opensphere_v0 single branch https github com ydwen opensphere git setup the environment cd opensphere conda env create f environment yml download the dataset bash scripts dataset_setup sh train the sphereface2 model cuda_visible_devices 0 1 python train py config config train vggface2_sfnet20_sphereface2 yml or train the sphereface model cuda_visible_devices 0 1 python train py config config train vggface2_sfnet20_sphereface yml test the model cuda_visible_devices 0 1 python test py config config test ijbb yml see our github page for detailed instructions citation if this framework helps your research please consider to cite article liu2022spherefacer title sphereface revived unifying hyperspherical face recognition author liu weiyang and wen yandong and raj bhiksha and singh rita and weller adrian journal ieee transactions on pattern analysis and machine intelligence year 2022 article wen2022sphereface2 title sphereface2 binary classification is all you need for deep face recognition author wen yandong and liu weiyang and weller adrian and raj bhiksha and singh rita booktitle iclr year 2022 inproceedings liu2017sphereface title sphereface deep hypersphere embedding for face recognition author liu weiyang and wen yandong and yu zhiding and li ming and raj bhiksha and song le booktitle cvpr year 2017 inproceedings liu2016lsoftmax title large margin softmax loss for convolutional neural networks author liu weiyang and wen yandong and yu zhiding and yang meng booktitle icml year 2016