Created by: jeng1220

IPlugin*::initialize and IPlugin*::terminate should be always implemented as a pair. Also, resources acquired in IPlugin*::initialize should be released in IPlugin*::terminate. Otherwise, it causes memory leak.

The all data members of cloned plugin must be set in PluginV2::clone. The plugin only calls IPlugin*::initialize once when creating ICudaEngine. The cloned plugin won't call IPlugin*::initialize after IExecutionContext is created, but TensorRT may clone the plugin during the creation of IExecutionContext and use the cloned plugin to infer the model.

Read https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#ipluginext to know more.