Downloads · 30 days
0
tactile-vae
WitneyWW/tactile-vae
tactile-vae is a machine learning model from WitneyWW. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
ViT-based tactile variational autoencoder.
Access
Public
Updated May 18, 2026
Repo size
248 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt246 MB · 98%
At a glance
- Access
- Public
- Created
- May 18, 2026
- Updated
- May 18, 2026
- SHA
- b952694d
Model card
From the Hugging Face model README
tactile_vae
ViT-based tactile variational autoencoder.
Architecture
- Encoder:
PatchEmbed + Transformer blocks + fixed sin-cos positional embedding - Latent:
mu/logvar+ reparameterization - Decoder: latent-conditioned transformer patch decoder + unpatchify
Usage
import torch
from tactile_vae.model import TactileVAE, VAELoss
model = TactileVAE()
out = model(torch.randn(2, 3, 128, 128))
loss_fn = VAELoss(beta=1.0)
losses = loss_fn(out["x_hat"], torch.randn(2, 3, 128, 128), out["mu"], out["logvar"])
- Created
- May 18, 2026
- Updated
- May 18, 2026