# Error when converting from ONNX model to Tensorrt

**URL:** <https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251>\
**Category:** Jetson AGX Xavier\
**Tags:** tensorrt, onnx, cuda\
**Created:** [August 6, 2023, 10:45pm UTC](https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251 "2023-08-06T22:45:58Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![ckm26](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ckm26](https://forums.developer.nvidia.com/u/ckm26)\
**Post date:** [August 6, 2023, 10:45pm UTC](https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251/1 "2023-08-06T22:45:59Z")

</div>

I am trying to convert MobileSAM ONNX to tensorrt on Jetson AGX Xavier and I have been getting the following error which I am unable to resolve. Could you please guide me on how to solve?

[08/06/2023-01:11:33] [V] [TRT] ModelImporter.cpp:103: Parsing node: /Split [Split]  
[08/06/2023-01:11:33] [V] [TRT] ModelImporter.cpp:119: Searching for input: /Expand\_2\_output\_0  
[08/06/2023-01:11:33] [V] [TRT] ModelImporter.cpp:119: Searching for input: /Constant\_29\_output\_0  
[08/06/2023-01:11:33] [V] [TRT] ModelImporter.cpp:125: /Split [Split] inputs: [/Expand\_2\_output\_0 → ()], [/Constant\_29\_output\_0 → (1)],  
ERROR: onnx2trt\_utils.cpp:188 In function convertAxis:  
[8] Assertion failed: axis \>= 0 && axis \< nbDims  
[08/06/2023-01:11:33] [E] Failed to parse onnx file  
[08/06/2023-01:11:33] [E] Parsing model failed  
[08/06/2023-01:11:33] [E] Engine creation failed  
[08/06/2023-01:11:33] [E] Engine set up failed

CUDA version: 10.2  
ONNX version : 1.14.0  
Tensorrt version: 7.1.3.0  
Jetpack version: 4.4.1

I have also attached my onnx file.

[mobile\_sam.onnx](https://forums.developer.nvidia.com/uploads/short-url/gs9qbcllyKszPyXOFCQs4AmNxP.onnx) (15.7 MB)

---

<div class="post-metadata">

**Author:** ![kayccc](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kayccc/32/14043_2.png) [@kayccc](https://forums.developer.nvidia.com/u/kayccc)\
**Post date:** [August 16, 2023, 4:07am UTC](https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251/6 "2023-08-16T04:07:40Z")

</div>

Sorry for the late response, our team will do the investigation and provide suggestions soon. Thanks

---

<div class="post-metadata">

**Author:** ![SivaRamaKrishnaNV](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/sivaramakrishnanv/32/14043_2.png) [@SivaRamaKrishnaNV](https://forums.developer.nvidia.com/u/SivaRamaKrishnaNV)\
**Post date:** [August 16, 2023, 10:32am UTC](https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251/8 "2023-08-16T10:32:35Z")

</div>

**There is no update from you for a period, assuming this is not an issue any more.  
Hence we are closing this topic. If need further support, please open a new one.  
Thanks**

Dear @ckm26,  
Could you share the used command. Also, is it possible to test with latest release (Jetpack 5.1.2)?

---

<div class="post-metadata">

**Author:** ![kayccc](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kayccc/32/14043_2.png) [@kayccc](https://forums.developer.nvidia.com/u/kayccc)\
**Post date:** [August 29, 2023, 8:21am UTC](https://forums.developer.nvidia.com/t/error-when-converting-from-onnx-model-to-tensorrt/262251/10 "2023-08-29T08:21:00Z")

</div>

Closed on August 29, 2023, 8:21am UTC