How to call onnx in onnx runtime web with dynamic input shape(ignoring input shape check)

Question

I use python get my onnx input shape

providers = ['AzureExecutionProvider', 'CPUExecutionProvider']  # Specify your desired providers
sess_options = onnxruntime.SessionOptions()
sess = onnxruntime.InferenceSession(model_path, sess_options, providers=providers)
input_shape = sess.get_inputs()[0].shape
print(f"Input shape: {input_shape}")

it show

Input shape: ['input_dynamic_axes_1', 'input_dynamic_axes_2', 'input_dynamic_axes_3', 'input_dynamic_axes_4']

when I run onnx in js

  const session = await ort.InferenceSession.create(model, {
    executionProviders: ["webgpu", "webgl"],
  });
  const feeds: any = {};
  const inputNames = session.inputNames;
  feeds[inputNames[0]] = inputTensor;
  const results = await session.run(feeds);
  const outputData = results[session.outputNames[0]].data;
  return outputData as any;

it raise err

    Uncaught (in promise) Error: input tensor[0] check failed: expected shape '[,,,]' but got [1,3,800,400]
      validateInputTensorDims   
      normalizeAndValidateInputs    
      (anonymous function)  
      event 
      run   
      run   
      run   
      runInference  

I think the reason is onnx input shape are dynamic, so following onnx js code always set expectedDim == [null, null,null,null]

  private validateInputTensorDims(
      graphInputDims: Array<readonly number[]>, givenInputs: Tensor[], noneDimSupported: boolean) {
    for (let i = 0; i < givenInputs.length; i++) {
      const expectedDims = graphInputDims[i];
      const actualDims = givenInputs[i].dims;
      if (!this.compareTensorDims(expectedDims, actualDims, noneDimSupported)) {
        throw new Error(`input tensor[${i}] check failed: expected shape '[${expectedDims.join(',')}]' but got [${
            actualDims.join(',')}]`);
      }
    }
  }

So my question is: how to call onnx in onnx runtime web with dynamic input shape(ignoring input shape check)