Tensor volume exceeds (2^31)-1

I trained a Tacotron2 model refrence from GitHub - Rayhane-mamah/Tacotron-2: DeepMind's Tacotron-2 Tensorflow implementation.
I convert onnx sucessfully and the result is correct. Hower a large tensor error occured when convert onnx into trt.

trt: 8.2.3
cuda: 10.2
cudnn: 7.6.5
onnx: 1.10.0
opset: 13


  • convert ckpt to onnx
  • simplifier onnx
  • convert onnx into trt

[02/14/2022-07:28:27] [E] [TRT] ModelImporter.cpp:776: — End node —
[02/14/2022-07:28:27] [E] [TRT] ModelImporter.cpp:779: ERROR: ModelImporter.cpp:166 In function parseGraph:
[6] Invalid Node - generic_loop_Loop__183
[graphShapeAnalyzer.cpp::processCheck::581] Error Code 4: Internal Error ((Unnamed Layer* 755) [LoopOutput]_output: tensor volume exceeds (2^31)-1, dimensions are [2147483647,1,160])
[graphShapeAnalyzer.cpp::processCheck::581] Error Code 4: Internal Error ((Unnamed Layer* 755) [LoopOutput]_output: tensor volume exceeds (2^31)-1, dimensions are [2147483647,1,160])
[02/14/2022-07:28:34] [E] Failed to parse onnx file
[02/14/2022-07:28:34] [I] Finish parsing network model
[02/14/2022-07:28:34] [E] Parsing model failed
[02/14/2022-07:28:34] [E] Failed to create engine from model.
[02/14/2022-07:28:34] [E] Engine set up failed

I have moved the topic to TensorRT - This team may be in a better position to help.

We recommend you to check the below samples links in case of tf-trt integration issues.

If issue persist, We recommend you to reach out to Tensorflow forum.


Are you using tf2onnx to generate ONNX file?

I am also facing the same error and I have used tf2onnx to convert
Any help would be appreciated!


Currently, TRT does not support tensors with more than 2^31-1 elements.
We do not have a workaround except modifiying the network.

Thank you.

Can you clarify please why this limitation exist?
what its root cause to limit the tensor volume size and raise a runtime exception while performing the model inference operation while there are still available GPU RAM?
Why not enable the inference operation till there will not be enough available RAM memory?