Downloads · 30 days
0
hamer
Leo-TX/hamer
hamer is a machine learning model from Leo-TX. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Pre-trained checkpoints for HaMeR (Hand Mesh Recovery).
Access
Public
Updated Mar 29, 2026
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ckpt2.7 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 29, 2026
- Updated
- Mar 29, 2026
- SHA
- f64df318
Model card
From the Hugging Face model README
HaMeR — Hand Mesh Recovery Checkpoints
Pre-trained checkpoints for HaMeR (Hand Mesh Recovery).
License
MIT License — Copyright (c) 2023 UC Regents, Georgios Pavlakos
These checkpoints are redistributed under the original MIT License from the HaMeR repository. Full license text: https://github.com/geopavlakos/hamer/blob/main/LICENSE.md
Files
| File | Size | Description |
|---|---|---|
hamer.ckpt | 2.6 GB | Pre-trained HaMeR model weights |
model_config.yaml | 2.1 KB | Model architecture config |
dataset_config.yaml | 1.4 KB | Dataset config |
mano_mean_params.npz | 1.2 KB | MANO mean pose parameters |
Usage
from huggingface_hub import hf_hub_download
ckpt = hf_hub_download(repo_id="Leo-TX/hamer", filename="hamer.ckpt")
Citation
@inproceedings{pavlakos2024reconstructing,
title={Reconstructing Hands in 3{D} with Transformers},
author={Pavlakos, Georgios and Shan, Dandan and Radosavovic, Ilija and Kanazawa, Angjoo and Fouhey, David and Malik, Jitendra},
booktitle={CVPR},
year={2024}
}
- License
- mit
- Created
- Mar 29, 2026
- Updated
- Mar 29, 2026