onnx / onnx/models

Invalid input scale for mxnet_arcface in opset8

Open
#358 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

mxnet_arcface from opset8 is throwing error with invalid input scale

Which model does this pertain to?

mxnet_arcface

Describe the bug

[E:onnxruntime:, sequential_executor.cc:309 Execute] Non-zero status code returned while running BatchNormalization node. Name:'stage1_unit1_bn1' Status Message: Invalid input scale: NumDimensions() != 3;Run failed:PerformanceRunner::RunOneIteration caught exception: Non-zero status code returned while running BatchNormalization node. Name:'stage1_unit1_bn1' Status Message: Invalid input scale: NumDimensions() != 3;

Reproduction instructions

Run the model on Default CPU
ONNX Runtime Repository Used: onnxruntime
Branch: master

Build Command :

  • cd PATH/TO/onnxruntime/
  • ./build.sh --config RelWithDebInfo --build --update --build_wheel --parallel

Test Command : ./onnxruntime_perf_test -e cpu -m times -r 10 PATH/TO/mxnet_arcface/model.onnx

System Information
Linux Ubuntu 18.04:
Onnxruntime.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the mxnet_arcface model linked in the issue and reproduce the failure using the specified ONNX Runtime build and onnxruntime_perf_test command. Inspect the stage1_unit1_bn1 BatchNormalization node and its input scale in the opset8 model. Done means the model runs on the default CPU without the invalid input scale error.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.