[TensorRT] Assertion failed: format.hasValue() && "format not recognized or not supported"

When converting onnx model to tensorRT engine, it gives an error:

    Building TensorRT engine, FP16 available:0
    Max batch size:     32
    Max workspace size: 1024 MiB
    BUG] Assertion failed: format.hasValue() && "format not recognized or not supported"
    ../builder/cudnnPluginV2Builder.cpp:102
    Aborting...
    [ERROR] ../builder/cudnnPluginV2Builder.cpp (102) - Assertion Error in deduceTensorFormat: 0 (format.hasValue() && "format not recognized or not supported")
    terminate called after throwing an instance of 'std::runtime_error'
      what():  Failed to create object
    Aborted (core dumped)

Environment

TensorRT Version: 7.0.0
GPU Type: Quadro P4000
Nvidia Driver Version: Driver Version: 418.67
CUDA Version: 10.0
CUDNN Version: 7.6.3.30
Operating System + Version: Ubuntu 18.04
ONNX IR version: 0.0.6
Opset version: 11
Producer name: tf2onnx
Producer version: 1.6.0

From error msg, it seems data format is not supported by TensorRT.
Please refer to below link for TensorRT supported formats:
https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-601/tensorrt-developer-guide/index.html#data-format-desc

Thanks