I am trying to run this code : import tensorrt as trt import pycuda.driver as cuda import pycuda.autoinit f = open(“resnet18_detector.trt”, “rb”) #f = open(“resnet_engine.trt”, “rb”) runtime = trt.Runtime(trt.Logger(trt.Logger.WARNING)) engine = runtime.deserialize_cuda_engine(f.read()) cont…

Getting Error when trying to upload .TRT model

Morganh June 21, 2021, 7:54am 8

For .tlt model or .trt engine, end user can run with default tlt detectnet_v2 inference to do inference.
For .etlt model, end user can deploy it with deepstream.
For .trt engine, if you try to run with your own python code, you can refer to Developer Guide :: NVIDIA Deep Learning TensorRT Documentation , mentioned in Inferring resnet18 classification etlt model with python - #12 by Morganh

Topic		Replies	Views
TensorRT deserialize_cuda_engine() returns a None Object TensorRT tensorrt	7	3769	October 12, 2021
Error while running resnet18_detector.trt weights with Deepstream sdk DeepStream SDK	6	1411	October 12, 2021
Using TensorRT3.0 to convert tensorflow model to create TensorRT engine Jetson TX1	3	649	March 8, 2018
AttributeError: 'NoneType' object has no attribute 'create_execution_context' TensorRT tensorrt , python	1	611	February 11, 2021
Error in tensorrt test TRT file TensorRT tensorrt , onnx	3	1437	July 5, 2022
Cannot execute TensorRT samples TensorRT	2	926	May 2, 2018
Invalid model file extension Error for Inference using TensorRT engine TensorRT tensorrt	3	565	October 12, 2021
TF-TRT issue Jetson TX2	26	3987	October 18, 2021
Unable to perform inference using yolov3 in tensorrt samples TensorRT	1	851	October 14, 2019
Error 3 Cuda initialization while deserializing TensorRT model TensorRT	6	3926	September 7, 2020