tensorflow / tensorflow/models

How to run interleaved LSTM object detection on edgeTPU

Open
#10,208 0 comments 0 reactions 1 assignee View on GitHub

@srjoglekar246 is already working on this.

Since Oct 11, 2021.

models:research:odapi type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

Hi there,
I'm trying to inference the interleaved mobilenet v2 model on an edge-tpu with tflite. After freezing the graph I noticed that the graph contained both the small and large SSD model. I assume that this would mean that during inference both models would run.

In the paper "Looking Fast and Slow: Memory-Guided Mobile Video Object Detection" they would run either f_0 or f_1 to get new states or SSD outputs. Could I get some pointers on how to export the two models to run independently?

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.