tensorflow / tensorflow/models

"ValueError: ssd_mobilenet_v2 is not supported" when try to re-export ssdlite_mobilenet_v2_coco_2018_05_09

Open
#9,104 0 comments 1 reaction 3 assignees View on GitHub

@pkulzc is already working on this.

Since Sep 8, 2020.

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

Description

Prerequisites

Please answer the following question for yourself before submitting an issue.

  • [ X] I checked to make sure that this issue has not been filed already.

1. The entire URL of the documentation with the issue

https://github.com/tensorflow/models/blob/v2.3.0/research/object_detection/g3doc/detection_model_zoo.md
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md

2. Describe the issue

Our frozen inference graphs are generated using the v1.12.0 release version of Tensorflow and we do not guarantee that these will work with other versions; this being said, each frozen inference graph can be regenerated using your current version of Tensorflow by re-running the exporter, pointing it at the model directory as well as the corresponding config file in samples/configs.

When I try the suggestion with tensorflow r2.3.0, it seems that some models are not supported by the model_builder.py

ValueError: ssd_mobilenet_v2 is not supported. See `model_builder.py` for features extractors compatible with different versions of Tensorflow

similarily,

ValueError: ssd_mobilenet_v1 is not supported. See `model_builder.py` for features extractors compatible with different versions of Tensorflow

Reason I tried to re-export to tf2 is that,

I actually ran the frozen graph of the available mobile models as is on RPI2 (4-core), and with

  • coco_ssd_mobilenet_v1_1.0_quant_2018_06_29 inference time is ~300ms, cpu usage is ~300% (Available 400%)
  • ssd_mobilenet_v3_small_coco_2020_01_14 inference time is ~500ms, cpu usage is ~90% (Available 400%)

What puzzels me is that v3 small takes much longer to inference a frame, but its cpu usage is way too low, indicating that a large portion of the ~500ms is spent on memory I/O ?

I don't know if that is caused by the model not exported from tf2.0, hence I tried to re-export it, and run into the stated error above.

Any suggestions?

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.