Releases: huggingface/pytorch-image-models
Mirror of ResNeSt weights
These are a mirror of weights from the official repository (https://github.com/zhanghang1989/ResNeSt ) to avoid issues with hosting changes/relocation
RegNet official weights (remapped and cleaned)
RegNet weights cleaned and remapped from https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md
Changes:
- first layer remapped from BGR to RGB
- cleaned out training details such as optimizer state, etc and leave just model state_dict (1/2 size)
- map layer names to mine
TResNet weights
Weights copied and cleaned (just state dict) from https://github.com/mrT23/TResNet/blob/master/MODEL_ZOO.md and other MIIL weight releases hosted at (*.aliyuncs.com) for more consistent/fast transfer speeds and avoidance of downtime.
SelecSLS Weights
These weights are re-hosted from original repository (https://github.com/mehtadushy/SelecSLS-Pytorch) with permission of the author, Dushyant Mehta (@mehtadushy), under a CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/legalcode) license.
SelecSLS (core) Network Architecture as proposed in "XNect: Real-time Multi-person 3D
Human Pose Estimation with a Single RGB Camera, Mehta et al."
https://arxiv.org/abs/1907.00837
HRNet weights from official impl
HRNet weights downloaded from official impl OneDrive links at: https://github.com/HRNet/HRNet-Image-Classification. Rehosted here with SHA hash for hub/modelzoo download compatibility.
Res2Net weights
Res2Net weights from https://github.com/gasvn/Res2Net for easier/faster access from North America that's compatible with model_zoo load_url
Released on PyPi
Pretrained weights (from Cadene)
These weights have all originated from Cadene's Pretrained model repository: https://github.com/Cadene/pretrained-models.pytorch
I'm re-hosting some of the weights here that I use more often to reduce download times as the US/Canada to France link can be slow.
Pretrained weights
All weights present here were either trained by me with the code in this repository or ported by me from original implementations.