[TensorRT] ERROR: Network must have at least one output

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Ubuntu 16.04 LTS
GPU type:1050Ti
nvidia driver version:390.87
CUDA version:9.0
CUDNN version:7.13
Python version:3.5
TensorRT version: 5.0.0.10

My model is trained by pytorch and converted to onnx file.
When I useed onnx parser to build cuda engine ,the error appeared:
[TensorRT] ERROR: Network must have at least one output
pure virtual method called
terminate called without an active exception
Aborted (core dumped)

My code is uploaded here and onnx file,some detail is:
onnx file:[url]https://drive.google.com/open?id=19xSFuO8hl7Kgr479IXdBOsDEfOylRjlp[/url]
weights file:[url]https://drive.google.com/open?id=19XqJF16siYCL3QpmNypPx7T-RmTTAtFC[/url]
You also can find code here:[url]https://github.com/MoonBunnyZZZ/trt-debug[/url]

First step, using yolo/pt20nnx.py to convert model to onnx file
Second step, running yolo/onnx_yolov3.py to test

yolo-debug-engine.zip (12.6 KB)

2

@NVES

[url]https://github.com/MoonBunnyZZZ/trt-debug[/url]

3

I encountered the same problem. But it disappeared after I updated TensorRT to latest version: 5.0.2.6

4

I am using version: 5.0.2.6.

5

Does the problem still exist? Which python are you using by the way? I am currently using 3.5.6.