You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am convert this model from onnx to tensorrt engine.
when I had a test using polygraphy run --trt model.onnx command, and it appeared a error:
[E] 2: [myelinBuilderUtils.cpp::getMyelinSupportType::1270] Error Code 2: Internal Error (ForeignNode does not support data-dependent shape for now.)
[!] Invalid Engine. Please ensure the engine was built correctly
[E] FAILED | Runtime: 22.843s | Command: /home/osmagic/anaconda3/envs/pytorch/bin/polygraphy run --trt
I run the command polygraphy run --onnxrt model.onnx, and there is on error.
I searched for this error, found a relative issue 3372
It said: We still don't support this, but it's in our plan and there are some effort on it.
Is this feature supported now?
If not, how can I solve this error by modifying the source code?
How can I find out which operator is causing the error?
DDS(data-dependent shape) is still under active development and there are still some restriction. please check our developer guide and api doc for more information.
Description
I am convert this model from onnx to tensorrt engine.
when I had a test using
polygraphy run --trt model.onnx
command, and it appeared a error:I run the command
polygraphy run --onnxrt model.onnx
, and there is on error.I searched for this error, found a relative issue 3372
It said:
We still don't support this, but it's in our plan and there are some effort on it.
Is this feature supported now?
If not, how can I solve this error by modifying the source code?
How can I find out which operator is causing the error?
Environment
TensorRT Version: 10.0
NVIDIA GPU: GeForce RTX 3090
NVIDIA Driver Version: 535.161.08
CUDA Version: 12.2
Operating System: ubuntu22.04
Python Version (if applicable): 3.9.7
Tensorflow Version (if applicable):
PyTorch Version (if applicable): 2.2.1
Relevant Files
Model link:
onnx model link
The text was updated successfully, but these errors were encountered: