LibreHRNetw48-pose

Official HRNet-W48 384x288 COCO-17 top-down pose weights, repackaged for LibreYOLO.

This is a person-crop pose head. Its fixed input is one 384x288 RGB person crop; the checkpoint does not contain a person detector. LibreYOLO can compose the head with its default YOLO9 detector, another PersonDetector, explicit person_boxes, or cropped=True.

Source

Derived from leoxiaobin/deep-high-resolution-net.pytorch at commit 6f69e4676ad8d43d0d61b64b1b9726f0c369e7b1. The upstream repository license is Copyright (c) 2019 Leo Xiao and is MIT. Adapted implementation files also identify Microsoft and Bin Xiao.

Official source file: pose_hrnet_w48_384x288.pth

Source SHA-256: 95e0fec3194826d5e3f806ea89be68bbb84517b114c3a32b3058c56610b5ef61

Modifications

The original state dict is wrapped with LibreYOLO checkpoint metadata. Learned tensor keys, values, and dtypes are unchanged and strict-load into the native HRNet-W48 graph. The converted file is LibreHRNetw48-pose.pt, SHA-256 ab85504f323c43babdcbed6550f759d323efd0ffc284a0593043e108cd3c4df5. See weights/convert_hrnet_weights.py and docs/provenance/hrnet.md in the LibreYOLO source repository.

License

The official project distributes this checkpoint from its MIT-licensed model zoo but does not attach a separate checkpoint-specific license. This mirror's redistribution basis is the MIT license implied by the releasing project, not a claim of an independently confirmed per-file grant. Training-data rights remain separate. See LICENSE and NOTICE.