Missing tensor.name for all the input/output pb files in bertsquad-8.tar.gz
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 9.8k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
In text/machine_comprehension/bert-squad/model/bertsquad-8.tar.gz, there are input and output pb files.
Base on the README.md of BERT-Squad model, there should have 4 inputs and 3 outputs, without the tensor.name defined in the pb files, it is very hard to determine which input is which and the same apply to output too. Further, there are 4 output pb files, output_3.pb should be deleted.
| Filename | tensor.name |
|---|---|
| input_0.pb | unique_ids_raw_output___9:0 |
| input_1.pb | input_ids:0 |
| input_2.pb | input_mask:0 |
| input_3.pb | segment_ids:0 |
| output_0.pb | unique_ids:0 |
| output_1.pb | unstack:0 |
| output_2.pb | unstack:1 |
| There are only 3 outputs, this file should be deleted. |
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with text/machine_comprehension/bert-squad/model/bertsquad-8.tar.gz and compare its input and output PB files with the BERT-Squad README.md. Verify that the four inputs and three outputs have the specified tensor.name values, and that output_3.pb is absent from the archive.
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
- Clearly specified
- Newbie friendliness
- 35/100