ViTPose++ -- small
top-down human pose estimation: a person box in, seventeen joints out

Copyright 2022 The University of Sydney.
Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao.

Source:  https://huggingface.co/usyd-community/vitpose-plus-small
Project: https://github.com/ViTAE-Transformer/ViTPose
Paper:   ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
         (NeurIPS 2022), arXiv:2204.12484
         ViTPose++: Vision Transformer for Generic Body Pose Estimation
         (TPAMI 2023), arXiv:2212.04246
Licence: Apache-2.0 (full text in the LICENSE file beside this one)

The authors' own release is built on mmpose. This file derives from the PyTorch
conversion published on Hugging Face, under the same terms. It is not the byte stream
that repository serves: tools/fetch/vitpose.py verifies the safetensors against the
sha256 the Hub records, then writes the same tensors back out as an ordinary
checkpoint. No tensor is altered, renamed, cast or dropped. The source file is:
           model.safetensors  sha256 f7bad8ed09eeeb2a7de6b38faaa8a88d07838e23e9c06a2a782099bca7467cb9