tensorflow / tensorflow/models
How do I process multiple inputs at once during the Inference step?
Open
@pkulzc is already working on this.
Since Jun 19, 2020.
models:research:odapi
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
How do I process multiple inputs at once during the Inference step?
I have two idea.
First is 'Batch Inference'.
Change the shape of input. from [1, w, h, 3] to [n, w, h, 3].
This logic run right. But, not changed elapsed time.
Second is 'Attach Image Inference'.
Also, Change the shape of input. [1, w, h, 3] to [1, w+w, h+h, 3].
So, once run get 4 result. elapsed time is same.
But accuracy is not good.
So, How to run....???
Give me a solution
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.