How to use the TensorRT_OSS plugins (e.g. GridAnchorPlugin) inside TensorRT Docker Containerexit()


I’m trying to convert a Tensorflow Detection Model (Mobilenetv2) into an TensorRT Model. The input size is a rectangle (640x360[wxh]).
In the release notes for TensorRT 7.2.1_OSS it is claimed that the the GridAnchorRect_TRT plugin with rectangular feature maps is re-enabled.
(TensorRT OSS release v7.2.1 by rajeevsrao · Pull Request #835 · NVIDIA/TensorRT · GitHub)
Unfortunately the conversion is not working because during the building of the TRT Engine it can’t find the option GridAnchorRect_TRT (more information below).


TensorRT Version: 7.2.1
GPU Type: GTX1070
Nvidia Driver Version: 460.32.03
CUDA Version: 11.1
CUDNN Version: 8.0.4
Operating System + Version: Ubuntu18.04
Python Version (if applicable): 3.6.9
TensorFlow Version (if applicable): 1.15.3
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

The conversion is working with these files for a quadratic Input (300x300)

  1. Inside these file are the config informations for the UFF Parser (3.7 KB)

  2. These file convert the UFF File into TRT File (1.0 KB)

  3. frozen_inference_graph.pb (18.2 MB)

  4. frozen_inference_graph.uff (17.9 MB)

Steps To Reproduce


  1. Use TensorRT 7.2.1 Docker Container (pull)
  2. Start docker container (with mounted volume to host) and enter /opt/tensorrt/python, run the file (installs e.g. uff, graphsurgeon etc.)
  3. Download the TensorRT_OSS into /workspace directory inside the container. This directory is mounted as volume to the host.
    git clone -b master TensorRT
    cd TensorRT
    git submodule update --init --recursive
    export TRT_SOURCE=pwd``
  4. create build directory inside /workspace/TensorRT
    mkdir -p build && cd build
    cmake .. -DTRT_LIB_DIR=$TRT_RELEASE/lib -DTRT_OUT_DIR=pwd/out
    make -j$(nproc)

Know I have some folders inside /build e.g. /plugin, /samples etc…
In every /plugin folder is a Makefile but i cant start the make file with make (it is doing nothing)

  1. Transform my frozen_inference_graph.pb into .uff (working) and start building TRT engine (not working). The model files and conversion scripts are inside the hosted Volume.

root@8f250d1c3328:/workspace/uff/test5# python3
[TensorRT] ERROR: UffParser: Validator error: GridAnchor: Unsupported operation _GridAnchorRect_TRT
Building TensorRT engine, this may take a few minutes…
[TensorRT] ERROR: Network must have at least one output
[TensorRT] ERROR: Network validation failed.
Traceback (most recent call last):
File “”, line 27, in
buf = trt_engine.serialize()
AttributeError: ‘NoneType’ object has no attribute ‘serialize’


  • How can I use the option GridAnchorRect_TRT to transform my Model into a TRT Model?

  • Is my way correct or is there an easier way? (ONNX conversion isn’t working for me). I don’t want to install TesnorRT on my Computer.

  • Unfortunately the conversion isn’t working when i use the description from the TensorRT_OSS Github site (building a docker image is working but conversion is also not working). (GitHub - NVIDIA/TensorRT at release/7.2)

Thanks for any help

Hi, Request you to check the below reference links for custom plugin implementation.