Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

bert_module: fix inputs of export model #3815

Merged
merged 2 commits into from
Mar 11, 2022
Merged

bert_module: fix inputs of export model #3815

merged 2 commits into from
Mar 11, 2022

Commits on Mar 9, 2022

  1. bert_module: fix inputs of exported model 

    Exported ONNX model had to be passed with "attention_mask" and
"token_type_ids" inputs swapped to get correct output.

Changing the input order fixes this issue.
Also return a dict instead of list for correctly passing inputs.

Update relevant tests:
test_TokenClassificationModel_export_to_onnx
test_PunctuationCapitalizationModel_export_to_onnx
test_QAModel_export_to_onnx

Signed-off-by: Viraj Karandikar <[email protected]>
    @virajkarandikar
    virajkarandikar committed Mar 9, 2022
    Configuration menu
    Copy the full SHA
    079e148 View commit details
    Browse the repository at this point in the history

Commits on Mar 11, 2022

  1. Merge branch 'main' into vkarandikar/fix_bert_model_inputs

    @yzhang123
    yzhang123 authored Mar 11, 2022
    Configuration menu
    Copy the full SHA
    7da2e04 View commit details
    Browse the repository at this point in the history