Order size is not matching the number dimensions of TensorRT

[02/17/2020-09:58:06] [I] C:/tools/TensorRT-7.0.0.11/data/mnist/yolov3.uff
[02/17/2020-09:58:09] [E] [TRT] UffParser: Parser error: yolov3/darknet53_body/Conv/Conv2D: Order size is not matching the number dimensions of TensorRT
[02/17/2020-09:58:09] [E] Failure while parsing UFF file

bool build()
{
SampleUniquePtr parser{ createUffParser() };
parser->registerInput(“Placeholder”, nvinfer1::DimsCHW(3,416, 416), nvuffparser::UffInputOrder::kNCHW);

}

解决了

Hi,

We are deprecating Caffe Parser and UFF Parser in TensorRT 7. Could you please try using ONNX parser?

You also can use “trtexec” command line tool to understand performance and possibly locate bottlenecks.

Please find the below links for your reference:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#trtexec
https://github.com/NVIDIA/TensorRT/blob/release/6.0/samples/opensource/trtexec/README.md

If issue persist, please share the model and sample script so we can better help.

Thanks