# ONNX model has a newer ir\_version (0.0.4) than this parser was built against (0.0.3).

**URL:** <https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212>\
**Category:** TensorRT\
**Created:** [November 29, 2019, 7:23am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212 "2019-11-29T07:23:30Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![koosdupreez](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@koosdupreez](https://forums.developer.nvidia.com/u/koosdupreez)\
**Post date:** [November 29, 2019, 7:23am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/1 "2019-11-29T07:23:30Z")

</div>

I am trying to import an ONNX model and get this error…

```auto
WARNING: ONNX model has a newer ir_version (0.0.4) than this parser was built against (0.0.3).
While parsing node number 0 [Conv]:
ERROR: ModelImporter.cpp:296 In function importModel:
[5] Assertion failed: tensors.count(input_name)

```

I have Latest TensorRT 6.0x and latest ONNX installed…

This model was exported from pytorch using the ONNX exporter as per this sample: [torch.onnx — PyTorch master documentation](https://pytorch.org/docs/master/onnx.html)

any ideas ?

---

<div class="post-metadata">

**Author:** ![orong13](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@orong13](https://forums.developer.nvidia.com/u/orong13)\
**Post date:** [November 30, 2019, 5:25pm UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/2 "2019-11-30T17:25:14Z")

</div>

Hello,

I think that I have the same problem.

This is my configuration:  
Windows 10  
Pyton - 3.6.8  
torch-1.1.0.dist-info  
torchsummary-1.5.1.dist-info  
torchvision-0.3.0.dist-info  
TensorRT - 6.0.1.5  
CuDNN - 7.6.3  
CUDA - 9.0

I have a segNet CNN implemented by torch and I converted it to onnx using these commands:

```auto
dummy_input = torch.randn(1, 32, 400, 400, device='cuda')

input_names = ["Input"]
output_names = ["Output"]

torch.onnx.export(model, dummy_input, "segNet.onnx", verbose=True, input_names=input_names,
                  output_names=output_names)

```

At the beginning the command torch.onnx.export was failed due to unsupported max\_unpool2d command.  
So I updated the file symbolic.py inside the onnx directory of the torch package:

```auto
def max_unpool2d(g, self, indices, output_size):
    return g.op("max_unpool2d", self, indices, output_size)

```

After this update the operation torch.onnx.export startes ro work properly without any errors and a segNet.onnx file was successfully generated.

But when i activated this operation:

```auto
auto parsed = m_onnxParser->parseFromFile(
			fileName.string().c_str(), static_cast<int>(nvinfer1::ILogger::Severity::kINFO));

```

I got the following report:

```auto
----------------------------------------------------------------
Input filename: segNet.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: pytorch
Producer version: 1.1
Domain:
Model version: 0
Doc string:
----------------------------------------------------------------
WARNING: ONNX model has a newer ir_version (0.0.4) than this parser was built against (0.0.3).
While parsing node number 0 [Cast]:
ERROR: builtin_op_importers.cpp:727 In function importCast:
[8] Assertion failed: trt_dtype == nvinfer1::DataType::kHALF && cast_dtype == ::ONNX_NAMESPACE::TensorProto::FLOAT

```

Any help will be much appreciated

---

<div class="post-metadata">

**Author:** ![SunilJB](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/suniljb/32/14043_2.png) [@SunilJB](https://forums.developer.nvidia.com/u/SunilJB)\
**Post date:** [December 11, 2019, 10:37am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/3 "2019-12-11T10:37:08Z")

</div>

Hi,

Could you please share your script and model file so we can better help?

Thanks

---

<div class="post-metadata">

**Author:** ![koosdupreez](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@koosdupreez](https://forums.developer.nvidia.com/u/koosdupreez)\
**Post date:** [December 11, 2019, 11:33pm UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/4 "2019-12-11T23:33:04Z")

</div>

do you want the ONNX model and code used to load it in TRT?

or do you want the Pytorch model and script to convert to TRT ?

---

<div class="post-metadata">

**Author:** ![orong13](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@orong13](https://forums.developer.nvidia.com/u/orong13)\
**Post date:** [December 12, 2019, 7:51am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/5 "2019-12-12T07:51:23Z")

</div>

Hello,

I understand now, that my major problem with the TRT Onnx is differnet so I opened a new topic:  
[https://devtalk.nvidia.com/default/topic/1068292/tensorrt/custom-layer-plugin-tensorrtc-nvuffparser-iuffparser-vs-tensorrt-c-nvonnxparser-iparser/](https://devtalk.nvidia.com/default/topic/1068292/tensorrt/custom-layer-plugin-tensorrtc-nvuffparser-iuffparser-vs-tensorrt-c-nvonnxparser-iparser/)

good luck here.

---

<div class="post-metadata">

**Author:** ![SunilJB](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/suniljb/32/14043_2.png) [@SunilJB](https://forums.developer.nvidia.com/u/SunilJB)\
**Post date:** [December 12, 2019, 8:56am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/6 "2019-12-12T08:56:36Z")

</div>

> [@](#):
>
> do you want the ONNX model and code used to load it in TRT?
> 
> or do you want the Pytorch model and script to convert to TRT ?

Hi,

Can you provide the following information so we can better help?  
Provide details on the platforms you are using:  
o Linux distro and version  
o GPU type  
o Nvidia driver version  
o CUDA version  
o CUDNN version  
o Python version [if using python]  
o Tensorflow and PyTorch version  
o TensorRT version

Also, if possible please share the script & model (pytorch and ONNX) file to reproduce the issue.

Thanks

---

<div class="post-metadata">

**Author:** ![nima](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@nima](https://forums.developer.nvidia.com/u/nima)\
**Post date:** [April 8, 2020, 4:30am UTC](https://forums.developer.nvidia.com/t/onnx-model-has-a-newer-ir-version-0-0-4-than-this-parser-was-built-against-0-0-3/108212/7 "2020-04-08T04:30:22Z")

</div>

I have same issue.  
Ubuntu 18.04  
GeForce GTX 1080ti  
Driver Version: 418.87.00  
CUDA Version: 10.1  
libcudnn.so.7.6.2  
python3.6  
tf 1.14  
tensorrt 6  
Deeplab model converted to onnx with tf2onnx with opset 11. But have this error in trtexec command:  
trtexec --onnx=frozen\_inference\_graph.onnx

WARNING: ONNX model has a newer ir\_version (0.0.6) than this parser was built against (0.0.3).  
While parsing node number 0 [Cast]:  
ERROR: builtin\_op\_importers.cpp:727 In function importCast:  
[8] Assertion failed: trt\_dtype == nvinfer1::DataType::kHALF && cast\_dtype == ::ONNX\_NAMESPACE::TensorProto::FLOAT  
[03/08/2020-09:00:00] [E] Failed to parse onnx file  
[03/08/2020-09:00:00] [E] Parsing model failed  
[03/08/2020-09:00:00] [E] Engine could not be created