Faith Xu comments

Results 17 comments of


                                            Faith Xu

Bump numpy from 1.21.0 to 1.22.0 in /tools/ci_build/github/linux/docker/scripts

/azp run onnxruntime-python-checks-ci-pipeline, orttraining-amd-gpu-ci-pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline

Bump numpy from 1.21.0 to 1.22.0 in /tools/ci_build/github/linux/docker/scripts

@snnn any concerns with this update?

Bump numpy from 1.21.0 to 1.22.0 in /tools/ci_build/github/linux/docker/scripts/training/ortmodule/stage1/requirements_torch1.11.0_rocm5.1.1

CC @askhade

Invalid input scale for mxnet_arcface in opset8

see https://github.com/onnx/models/issues/242 workaround is described in https://github.com/microsoft/onnxruntime/issues/2447

Pad is not registered for mask_rcnn_keras from opset10

which version of ORT are you using?

operator MaxPool output tensor shape is ambiguously documented.

Stalebot closes issues without activity. @srohit0 looks like this is already tracked in #3651 now - can you follow up there?

Got segmentation fault error when using 'InferenceSession' API

CC @pranavsharma