How to modify config.py for different model in model zoo of tensorflow object detection to generate UFF?

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I have converted given example SSD_300x300 model frozen graph to UFF.
Similarly, I want to try other models which have better mAP value than SSD_300x300 from tensorflow model zoo: [url]https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md[/url]
How do I change config.py for those models in order to convert frozen graphs of those models to UFF? Does tensorRT support all the object detection models from the model zoo? If No, What are the limitations?

2

Hello,

TensorRT support is limited to the types of layers used by the object detection model zoo;

In this case, users can extend TensorRT functionalities by implementing custom layers using the IPluginExt class for the C++ and Python API. Custom layers, often referred to as plugins, are implemented and instantiated by an application, and their lifetime must span their use within a TensorRT engine.