NVIDIA / NVIDIA/Deep-Learning-Accelerator-SW
Error when calibrating generated model using calibration cache file for tensorrt 10.3.0
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 236
- Forks
- 24
- PR merge metrics
- No merged PRs in 30d
Description
I am trying to convert onnx model to tensorrt egnine. I am using trtexec utility for doing this. Engine file should run in int8 so i generated a calibration file using qdqtranslator . But when using the calibration file to convert to int8 , trtexec fails with error
[E] Error[3]: IExecutionContext::executeV2: Error Code 3: API Usage Error (Parameter check failed, condition: nullPtrAllowed. Tensor “input” is bound to nullptr, which is allowed only for an empty input tensor, shape tensor, or an output tensor associated with an IOuputAllocator.)
What could be causing this ? Is calibration file compatible with tensorrt 10.3.0 ?
Header of cache file looks like this
TRT-8600-EntropyCalibration2 input: 3d23ac36 /init_block/pool/MaxPool_output_0: 3e5b2be4 /stage1/unit1/body/conv1/activ/Relu_output_0: 3e540b45
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the ONNX-to-TensorRT conversion with trtexec, using the calibration cache generated by qdqtranslator and TensorRT 10.3.0. Check whether the cache header and tensor entries are compatible, then determine why the input tensor is bound to nullptr; done means identifying the compatibility or binding cause and documenting a verified resolution.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100