tensorflow / tensorflow/models
Turn Object detection model in a Image classification model
Open
Nobody has claimed this yet.
models:research
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
I'm struggling with MLKit by Google for an android application.
Turn out that MLKit doesn't support REAL object detection(models): for each possible object identified (not by the model!), MLKit make an inference made by the model [which is a classification model].
Knowing that the outputs of Object detection model are different from Image classification model (in my case the output of the net need to be like 2D (BxN with B=1) or 4D (BxHxWxN with B=1, W=1, H=1) )
I'm wondering if is possible to manipulate a model output for my case.
Thanks!
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.
Assessment
This issue has not been assessed yet.