hassamdevsy / mask2former

Facebook Mask2Former trained on ADE 20k Dataset (Updated 1 year, 11 months ago)

  • Public
  • 57K runs
  • GitHub
  • Paper

Input

image
*file

Output

objects

[ { "color": [ 120, 120, 120 ], "label": "wall" }, { "color": [ 80, 50, 50 ], "label": "floor" }, { "color": [ 120, 120, 80 ], "label": "ceiling" }, { "color": [ 255, 6, 82 ], "label": "table" }, { "color": [ 255, 51, 7 ], "label": "curtain" }, { "color": [ 204, 70, 3 ], "label": "chair" }, { "color": [ 255, 6, 51 ], "label": "painting" }, { "color": [ 11, 102, 255 ], "label": "sofa" }, { "color": [ 255, 9, 92 ], "label": "rug" }, { "color": [ 8, 255, 214 ], "label": "armchair" }, { "color": [ 224, 255, 8 ], "label": "lamp" }, { "color": [ 255, 194, 7 ], "label": "cushion" }, { "color": [ 0, 255, 112 ], "label": "coffee" }, { "color": [ 255, 0, 0 ], "label": "flower" }, { "color": [ 255, 173, 0 ], "label": "light" }, { "color": [ 0, 41, 255 ], "label": "sconce" }, { "color": [ 0, 245, 255 ], "label": "fan" } ]

segment

segment
Generated in

This output was created using a different version of the model, hassamdevsy/mask2former:3bc93de0.

Run time and cost

This model costs approximately $0.021 to run on Replicate, or 47 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 94 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.