tensorRT5.1.5 parse yolov3.onnx occurs error

i download yolov3.onnx from this site: https://github.com/onnx/models/tree/master/vision/object_detection_segmentation/yolov3
I run tensorRT5.1.5 samples and modified sample_onnx_mnist to parse the yolov3.onnx, but occurs error below:

(mypy35) xiaoga@xiaoga-Lenovo:~/到 TensorRT-5.1.5.0 的链接/bin$ ./sample_onnx_mnist
&&&& RUNNING TensorRT.sample_onnx_mnist # ./sample_onnx_mnist
----------------------------------------------------------------
Input filename:   ../../../data/mnist/yolov3_modelzoom.onnx
ONNX IR version:  0.0.5
Opset version:    10
Producer name:    keras2onnx
Producer version: 1.5.1
Domain:           onnx
Model version:    0
Doc string:       
----------------------------------------------------------------
WARNING: ONNX model has a newer ir_version (0.0.5) than this parser was built against (0.0.3).
[E] [TRT] Parameter check failed at: ../builder/Network.cpp::addInput::465, condition: isValidDims(dims)
ERROR: ModelImporter.cpp:80 In function importInput:
[8] Assertion failed: *tensor = importer_ctx->network()->addInput( input.name().c_str(), trt_dtype, trt_dims)
[E] Failure while parsing ONNX file
&&&& FAILED TensorRT.sample_onnx_mnist # ./sample_onnx_mnist
sample_onnx_mnist: sampleOnnxMNIST.cpp:212: int main(int, char**): Assertion `trtModelStream != nullptr' failed.
已放弃 (核心已转储)

Please give some advice for this problem and thanks very much.

Reproduce the failure with sample_onnx_mnist and the referenced yolov3_modelzoom.onnx input, then inspect sampleOnnxMNIST.cpp around line 212 and the ONNX parser output. Check the TensorRT 5.1.5 parser's supported IR version and input dimensions; done means the model parses without the addInput assertion and the sample proceeds past model creation.