onnx / onnx/models

[BERT-Squad][opset-10] Mismatch between expected values of ONNX and output_0.pb & output_2.pb

Open
#428 0 comments 2 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

I just inspected the commit 5f39d25

image

  • unstack:1 TensorFloat shape(-1,256)
  • unstack:0 TensorFloat shape(-1,256)
  • unique_ids:0 TensorInt64Bit shape(-1)

Unpacked into folder

  • [bertsquad-10]
    • [test_data_set_1]
      • output_0.pb => expected "unstack:1" but "unique_ids:0" TensorFloat shape(-1,256)
      • output_1.pb => expected "unstack:0" YES"unstack:0" TensorFloat shape(-1,256)
      • output_2.pb => expected "unique_ids:0" but "unstack:1" TensorInt64Bit shape(-1)
  • bertsquad10.onnx

Other relevant open issues

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 commit 5f39d25, bertsquad10.onnx, and bertsquad-10/test_data_set_1/output_0.pb through output_2.pb. Compare the recorded output names, types, and shapes with the expected order, then review issues 415, 406, 216 and pull request 420 for the project’s intended convention. Done means the model artifacts and expected results agree without leaving the reported mismatch.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 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.