Skip to content

Run semantic segmentation sample on full GPU pipeline #124

Open
@huningxin

Description

@huningxin

This is required by webmachinelearning/webnn#226

To implement this pipeline, the semantic segmentation sample probably could execute following steps:

  1. Use mediacapture-transform to capture the VideoFrame
  2. Import the VideoFrame into a WebGPU texture (GPUExternalTexture)
  3. Execute WebGPU shader to do pre-processing and convert the GPUExternalTexture to a GPUBuffer
  4. Compute the MLGraph with converted GPUBuffer and the output is another GPUBuffer
  5. Execute WebGPU shader to do post-processing on the output GPUBuffer and render the result to a canvas.
  6. Create a VideoFrame from the CanvasImageSource and enqueue to the mediacapture-transform API's controller.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions