-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error Code 4: Internal Error (Network must have at least one output) #1728
Comments
@Tian14267
have you tried:
If this not works, we have to wait next one or two major release, which support N-D shape tensor feature to fix this. |
Hi! Any update on this? I'm facing a similar issue. |
ND shape tensor will be supported in the next version after TRT 8.4 GA |
Problem solved, thanks for the solution~ |
Closing since it is fix, thanks! |
@zzg-tju How did you solve this? |
Description
I covert my onnx model into trt , but I get this error :
Error Code 4: Internal Error (Network must have at least one output)
detail error is :
Here is My code:
Here is my onnx_model
My onnx is like this:
Environment
TensorRT Version: TensorRT-8.2.1.8
NVIDIA GPU: GeForce RTX 3090
NVIDIA Driver Version:
CUDA Version: 11.2
CUDNN Version:
Operating System: centos 7
Python Version (if applicable): 3.6
Tensorflow Version (if applicable): 1.15.4
PyTorch Version (if applicable): 1.8.1
Baremetal or Container (if so, version):
Can anybody help me ?
The text was updated successfully, but these errors were encountered: