builder_->buildCudaEngine(*network_) return nullptr

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

Description

When I run “builder → buildCudaEngine(* network)”, the nullptr will return, what could be the reason?

I used it on ubuntu, how can I view the stack of “nvinfer1”，does it have an open source code?

I had set a logger, and print log level above “Severity::kINFO”. But I found nothing. How could I see the debug info?

I will add the detail version latter, could you please give some advice first.

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
3

Hi @daohu527,
Please refer the following link.
https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_builder.html

4

There is no helpful info, could you pls give me some method for debug,or some list of reasons will be ?

5

Hi @daohu527,

Please enable kVERBOSE to dump more logs.

Thank you.