microsoft / microsoft/microxcaling
Large accuracy loss on MobileVit model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 364
- Forks
- 53
- PR merge metrics
- No merged PRs in 30d
Description
Hello everyone,
I would like to reproduce the results in the paper.
When converting to MX format on various models,
I found that MobileVit experiences a significant accuracy loss (accuracy<1%),
However this issue does not occur with ResNet-18 20 and 50.
I would like to ask if anyone else has encountered this situation and how to resolve it .
Thank you!
Contributor guide
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 by reproducing the reported MobileVit conversion to MX and compare its accuracy with the ResNet-18, 20, and 50 results mentioned in the issue. No file, test, or entry point is named, so identify the conversion and evaluation entry points first; done means determining the cause of the sub-1% accuracy and documenting a verified resolution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100