Mask2Former Swin-T ADE20K semantic (ONNX, 512 x 512) for Perspectra

Redistribution of an existing open model, converted for the Perspectra Blender add-on. No retraining.

Original work: Meta AI, Mask2Former (https://github.com/facebookresearch/Mask2Former), weights facebook/mask2former-swin-tiny-ade-semantic
Licence: MIT — the same as the original weights. All credit to the original authors.
Paper: Cheng et al., Masked-attention Mask Transformer for Universal Image Segmentation, CVPR 2022
Used for people / sky / water / plants masks (ADE20K classes).

File	Size	SHA-256
`mask2former_swint_ade_512.onnx`	193 MB	`eb59758c041fcba3…`

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support