Downloads · 30 days
348
3% of all-time downloads
hvae
zeahub/hvae
hvae is a machine learning model from zeahub. 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 apache-2.0.
Generative model for 2D B-mode Ultrasound Images. This model can be used for unconditional sampling as well as inpainting tasks.
All-time downloads
10.6K
Public
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h5908 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 12, 2025
- Updated
- Jan 15, 2026
- SHA
- 54250837
Model card
From the Hugging Face model README
Hierarchical Variational Autoencoder (HVAE)
Generative model for 2D B-mode Ultrasound Images. This model can be used for unconditional sampling as well as inpainting tasks.
Current architecture in this folder is only trained on resolution 256x256x3 (3 video frames per input/output).
🌽 The zea implementation is a snippet, adapted from the source.
The weights that are currently present can be read as follows:
lvh: trained onEchonetLVHdatasetur: encoder retrained with UniformRandomLines subsamplingzea.agentge: encoder retrained with GreedyEntropy subsamplingzea.agent24: 24 lines/columns used when subsampling
📚 A usage tutorial can be found on Collab
- License
- apache-2.0
- Created
- Dec 12, 2025
- Updated
- Jan 15, 2026