tensorflow / tensorflow/models

How do I process multiple inputs at once during the Inference step?

Open
#7,192 2 comments 1 reaction 3 assignees View on GitHub

@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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.