mmdetection: INVALID_ARGUMENT: getPluginCreator could not find plugin NonMaxSuppression version 1

I have successfully converted yolov3 pytorch model to onnx and then tensorrt by the tools：pytorch2onnx.py and onnx2tensorrt.py, but when i use tensorrt do inference, it gives me the errors:

[TensorRT] ERROR: INVALID_ARGUMENT: getPluginCreator could not find plugin NonMaxSuppression version 1 [TensorRT] ERROR: safeDeserializationUtils.cpp (322) - Serialization Error in load: 0 (Cannot deserialize plugin since corresponding IPluginCreator not found in Plugin Registry) [TensorRT] ERROR: INVALID_STATE: std::exception [TensorRT] ERROR: INVALID_CONFIG: Deserialize the cuda engine failed. Traceback (most recent call last): File “onnx_to_tensorrt.py”, line 106, in <module> main() File “onnx_to_tensorrt.py”, line 73, in main with get_engine(engine_file_path) as engine, engine.create_execution_context() as context: AttributeError: enter

The onnx_to_tensorrt.py file as below:

def get_engine(engine_file_path=“”):

if os.path.exists(engine_file_path):
    # If a serialized engine exists, use it instead of building an engine.
    print("Reading engine from file {}".format(engine_file_path))
    with open(engine_file_path, "rb") as f, trt.Runtime(TRT_LOGGER) as runtime:
        return runtime.deserialize_cuda_engine(f.read())
return None`

def main():

engine_file_path = "yolov3.trt"
input_image_path = 'images/00076.jpg'
image = Image.open(input_image_path)
image = np.transpose(image, [2, 0, 1])
trt_outputs = []
with get_engine(engine_file_path) as engine, engine.create_execution_context() as context:
    inputs, outputs, bindings, stream = common.allocate_buffers(engine)
    # Do inference
    print('Running inference on image {}...'.format(input_image_path))
    # Set host input to the image. The common.do_inference function will copy the input to the GPU before executing.
    inputs[0].host = image
    trt_outputs = common.do_inference_v2(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream)
    print(trt_outputs)

I’m not sure it is the correct way to use the ‘.trt’ file. Could you give me some suggestions? Ubuntu-16.04 pytorch 1.6 cuda 10.2 tensorrt 7.2.1.6 mmcv 1.3.7 mmdet 2.13 onnx 1.7