Skip to content

canvit

pgpolicy-ade20k-c64-t5-2026-07-05-s0

canvit/pgpolicy-ade20k-c64-t5-2026-07-05-s0

pgpolicy-ade20k-c64-t5-2026-07-05-s0 is a reinforcement learning model from canvit. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for canvit-pytorch. The card lists the license as mit.

A learned viewing policy: it scores candidate viewpoints from the canvas of the frozen CanViT-B and the segmentation its ADE20K probe reads out of the canvas, and CanViT-B looks next at the candidate of highest score.…

Downloads · 30 days

45

33% of all-time downloads

All-time downloads

138

Public

Parameters

5.5M

66.8 MB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt22.3 MB · 47%

At a glance

Task
Reinforcement Learning
Library
canvit-pytorch
License
mit
Access
Public
Created
Jul 5, 2026
Updated
Oct 29, 2026
SHA
29625b19

Base models

Task
Reinforcement Learning
Library
canvit-pytorch
License
mit
Created
Jul 5, 2026
Updated
Oct 29, 2026