Int8 Models using custom Ops in the model zoo
Open
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
Bug Report
Which model does this pertain to?
I haven't done an exhaustive search so there are likely more. So far I've found:
- https://github.com/onnx/models/blob/main/vision/classification/alexnet/model/bvlcalexnet-12-int8.onnx
- https://github.com/onnx/models/blob/main/vision/classification/mobilenet/model/mobilenetv2-12-int8.onnx
Describe the bug
I found some models in the zoo contain a QLinearAdd which does not exist in the ONNX Operators list. (There are other QLinear* operators but no QLinearAdd)
Reproduction instructions
View models in Netron. Search for QLinearAdd
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
Open the two linked .onnx files in Netron and search for QLinearAdd; compare the operator name with the ONNX Operators list. Done means the affected model files are identified and the expected correction is established, since the issue does not specify a fix or target behavior.
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