[js/web] support 'pytorch_half_pixel' mode for WebGL kernel 'Resize'#11208
Conversation
|
|
|
/azp run ONNX Runtime Web CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
fs-eire
changed the title
|
/azp run ONNX Runtime Web CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
/azp run Windows CPU CI Pipeline, Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows WebAssembly CI Pipeline, orttraining-amd-gpu-ci-pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, onnxruntime-python-checks-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 Nuphar CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline |
|
Azure Pipelines successfully started running 8 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
| // handle exception when opset > 9 and roi not given | ||
| if (input === '' && nodeProto.input.length === 3 && nodeProto.opType === 'Resize') { | ||
| continue; | ||
| } |
There was a problem hiding this comment.
The old ONNX.js graph initialization does not support optional inputs. I will do another change to enable a general support on that.
|
The CI check "Python format" does not run and seems to block the merge. I tried several ways to trigger it but with no luck... @ncianeo could you do a merge to the latest master branch to trigger the CI to rerun the checks? |
|
/azp run ONNX Runtime Web CI Pipeline |
|
Commenter does not have sufficient privileges for PR 11208 in repo microsoft/onnxruntime |
|
/azp run Windows CPU CI Pipeline, Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows WebAssembly CI Pipeline, orttraining-amd-gpu-ci-pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, onnxruntime-python-checks-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 Nuphar CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline |
|
Azure Pipelines successfully started running 8 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
sophies927
added
platform:web
|
Hi, is there any progress on getting this in the javascript onnxruntime? It is preventing me from performing webgl based inference on any mainstream segmentation models, and the wasm backend is too slow. |
…icrosoft#11208) **Description**: 1. add pytorch_half_pixel interpolation mode in resize-packed.ts Changes: add the following case in createPackedResizeProgramInfo function: ``` case 'pytorch_half_pixel': getSourceFracIndex = ` vec4 getSourceFracIndex(ivec4 coords) { vec4 fcoords = vec4(coords); return vec4( ${outputWidth}.0 > 1.0 ? (fcoords.x + 0.5) / scaleWHWH.x - 0.5 : 0.0, ${outputHeight}.0 > 1.0 ? (fcoords.y + 0.5) / scaleWHWH.y - 0.5 : 0.0, ${outputWidth}.0 > 1.0 ? (fcoords.z + 0.5) / scaleWHWH.z - 0.5 : 0.0, ${outputHeight}.0 > 1.0 ? (fcoords.w + 0.5) / scaleWHWH.w - 0.5 : 0.0 ); } `; break; ``` 2. fix "unrecognized input '' for node: Resize_$num" error when inputs like [input_tensor, None, scale_factor] (roiInput not given) are fed into the resize layer. Changes: change in input handling logic in upsample.ts & node scanning logic in graph.ts **Motivation and Context** Before this fix, we aren't able to use webGL backend when the neural network contains pytorch resize layers. This fix adds 'pytorch_half_pixel' interpolation mode support and makes it possible to use webGL backend for more kind of computer vision networks. This commit solves: microsoft#10430 Co-authored-by: neo <neo@icode-lab.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
…icrosoft#11208) **Description**: 1. add pytorch_half_pixel interpolation mode in resize-packed.ts Changes: add the following case in createPackedResizeProgramInfo function: ``` case 'pytorch_half_pixel': getSourceFracIndex = ` vec4 getSourceFracIndex(ivec4 coords) { vec4 fcoords = vec4(coords); return vec4( ${outputWidth}.0 > 1.0 ? (fcoords.x + 0.5) / scaleWHWH.x - 0.5 : 0.0, ${outputHeight}.0 > 1.0 ? (fcoords.y + 0.5) / scaleWHWH.y - 0.5 : 0.0, ${outputWidth}.0 > 1.0 ? (fcoords.z + 0.5) / scaleWHWH.z - 0.5 : 0.0, ${outputHeight}.0 > 1.0 ? (fcoords.w + 0.5) / scaleWHWH.w - 0.5 : 0.0 ); } `; break; ``` 2. fix "unrecognized input '' for node: Resize_$num" error when inputs like [input_tensor, None, scale_factor] (roiInput not given) are fed into the resize layer. Changes: change in input handling logic in upsample.ts & node scanning logic in graph.ts **Motivation and Context** Before this fix, we aren't able to use webGL backend when the neural network contains pytorch resize layers. This fix adds 'pytorch_half_pixel' interpolation mode support and makes it possible to use webGL backend for more kind of computer vision networks. This commit solves: microsoft#10430 Co-authored-by: neo <neo@icode-lab.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
7 participants
Description:
Changes: add the following case in createPackedResizeProgramInfo function:
Changes: change in input handling logic in upsample.ts & node scanning logic in graph.ts
Motivation and Context
Before this fix, we aren't able to use webGL backend when the neural network contains pytorch resize layers. This fix adds 'pytorch_half_pixel' interpolation mode support and makes it possible to use webGL backend for more kind of computer vision networks.
This commit solves:
#10430