When I create a TensoRT engine from a UFF, ONNX, or some other serialized graph, plugins are automatically created for layers such as Non Max Suppression. This plugin’s parameters (such as DetectionOutputParameters) are fetched from the input UFF and the plugin object is created. However, in my code I have no way to retrieve these parameters, therefore I have to hard-code the values such as keepTopK in my code. Any changes to these in the model will require code changes. In order to improve portability, it would be really nice if we were able to find the plugin in the graph, get its parameters, and then be able to use these parameters in our program. That way, we could change our model without having to change our code. Hope NVIDIA considers this for upcoming releases and please comment if you’d find this feature useful.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Passing parameters to a TensorRT plugin | 8 | 1116 | October 18, 2021 | |
| there is anyway to get the params from .prototxt when create a plugin in tensorrt5.0? | 3 | 708 | October 12, 2021 | |
| How to read layer param. with TensorRT Plugin from .prototxt | 2 | 1682 | January 23, 2018 | |
| How to set parameters of BatchedNMSPlugin? | 5 | 671 | April 28, 2023 | |
| how to define plugin layer with param? | 2 | 990 | October 12, 2021 | |
| TensorRT Plugin data access | 1 | 336 | April 28, 2021 | |
| how to add plugin layer in tensorrt with tensorflow model. | 2 | 819 | October 18, 2021 | |
| Adding a custom layer plugin for ONNX graph | 2 | 560 | August 14, 2020 | |
| Adding Tensorrt Plugin to Deserialized Engine | 4 | 658 | March 5, 2021 | |
| A qustion about custom layer plugin when i use onnx parser | 3 | 417 | April 6, 2021 |