tensorflow / tensorflow/models

frozen inference graphs generated using the v1.12.0 release version of Tensorflow???

Open
#7,959 2 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Jun 4, 2020.

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

Description

According to you: "Our frozen inference graphs are generated using the v1.12.0 release version of Tensorflow..."

I find this information hard to believe. Let's say, the SSD MobileNet V2 COCO model, for example. It is quite clear from the time stamp that the model and graph were generated in MARCH 2018.
On the other hand, Tensorflow v1.12 was released in NOVEMBER of the same year.
So, how do you reconcile this discrepancy?

I am asking this because I have no issue converting the pre-trained model to ONNX or TensorRT. But when I re-train the model on my dataset using Tensorflow 1.12, the newly generated model fails to convert to either ONNX or TensorRT.
Please explain.

(P.S. Later we can get into the sort of errors I get, if you insist, but others have already reported on those problems).

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.