tensorflow / tensorflow/models

Tensorlfow to UFF to TensorRT conversion

Open
#8,817 2 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Jul 9, 2020.

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

Description

Hallo,
I have a problem with ssd inception v2 2017-11-17 model.

I want to train using my dataset of 38 classes and port it to UFF and run the inference in TensorRT on Jetson Nano.

I was successful with all the steps above for standard model : ssd_inception_v2_2017_11_17.
But when I retrain it using my data. I am not getting any detection boxes in TensorRT.

Tensorflow training is correct because I am getting detection results in tensorflow.

After the conversion to UFF and TensorRT, model is not detecting any output. also I am not getting any errors.
Could you please let me know what is the problem??
I am using
Tensorflow 1.14.0 version.
Object detection api: 11e9c7adfbf7d550dd9ef4442cf7806cdb2ee2368 from 2017 November 17

Let me know if I have to use different versions to reproduce the detections.
Thank you

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.