[WebNN] Remove validation for coordinate_transformation_mode #22811
Conversation
|
BTW, should WebNN add coordinate_transformation_mode as a parameter of Resize? There is a spec issue about it: webmachinelearning/webnn#270 @fdwr |
|
Ooh, nice table @Honry. We'd have to look at TFLite(EdgeRT) and CoreML first. DirectML supports basically any transformation mode with a scale factor and offsets. |
|
/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline |
|
/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline |
|
/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models |
|
Azure Pipelines successfully started running 2 pipeline(s). |
|
Azure Pipelines successfully started running 3 pipeline(s). |
|
Azure Pipelines successfully started running 4 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
(I'll update the CR description for you) |
Oh I didn't notice your comment above, thanks! :) |
…ft#22811) The performance cost of falling back to the CPU EP is high for several resampling nodes and causes multiple partitions in SD Turbo and VAE decoder. Since the asymmetric mode with nearest to floor and integer scales is identical to half_pixel anyway, stick with the WebNN EP.
The performance cost of falling back to the CPU EP is high for several resampling nodes and causes multiple partitions in SD Turbo and VAE decoder. Since the asymmetric mode with nearest to floor and integer scales is identical to half_pixel anyway, stick with the WebNN EP.
…ft#22811) The performance cost of falling back to the CPU EP is high for several resampling nodes and causes multiple partitions in SD Turbo and VAE decoder. Since the asymmetric mode with nearest to floor and integer scales is identical to half_pixel anyway, stick with the WebNN EP.
…ft#22811) The performance cost of falling back to the CPU EP is high for several resampling nodes and causes multiple partitions in SD Turbo and VAE decoder. Since the asymmetric mode with nearest to floor and integer scales is identical to half_pixel anyway, stick with the WebNN EP.
The performance cost of falling back to the CPU EP is high for several resampling nodes and causes multiple partitions in SD Turbo and VAE decoder. Since the asymmetric mode with nearest to floor and integer scales is identical to half_pixel anyway, stick with the WebNN EP.