Lack of understanding how to migrate SSD code written for TensorRT5 to the latest TensorRT7.
A clear and concise description of the bug or issue.
While migrating from TensorRT5 to TensorRT7 I stumbled into a lack of understanding how to correctly use the new V2 plugin system on c++. For example, calls like createSSDDetectionOutputPlugin or createSSDAnchorGeneratorPlugin are now deprecated. Is there an example how to use use SSD on TensorRT7?
Environment
Ngc tensorflow 20.8 docker container
TensorRT Version: 7 GPU Type: Titan V Nvidia Driver Version: 450.66 CUDA Version: 11 CUDNN Version: 8 Operating System + Version: Ubuntu 18.04.4 LTS Python Version (if applicable): 3.6.9 TensorFlow Version (if applicable): 20.8 PyTorch Version (if applicable): Baremetal or Container (if container which image + tag): Ngc tensorflow 20.8 docke
Hi @bnascimento,
We highly encourage you to move to IPluginV2IOExt or IPluginV2DynamicExt to be able to use all the new plugin functionalities.
Please refer to below sample for your reference: