Open huningxin opened 2 years ago
This is required by https://github.com/webmachinelearning/webnn/issues/226
To implement this pipeline, the semantic segmentation sample probably could execute following steps:
VideoFrame
GPUExternalTexture
GPUBuffer
CanvasImageSource
Related to https://github.com/webmachinelearning/webnn-polyfill/issues/156
depends on https://github.com/w3c/webcodecs/pull/412
This is required by https://github.com/webmachinelearning/webnn/issues/226
To implement this pipeline, the semantic segmentation sample probably could execute following steps:
VideoFrame
VideoFrame
into a WebGPU texture (GPUExternalTexture
)GPUExternalTexture
to aGPUBuffer
GPUBuffer
and the output is anotherGPUBuffer
GPUBuffer
and render the result to a canvas.VideoFrame
from theCanvasImageSource
and enqueue to the mediacapture-transform API's controller.