How to use the winrt.windows.ai.machinelearning.TensorFloat.create function in winrt

def bind_model(model, image_frame):
    device = winml.LearningModelDevice(winml.LearningModelDeviceKind.DEFAULT)
    session = winml.LearningModelSession(model, device)
    binding = winml.LearningModelBinding(session)
    image_feature_value = winml.ImageFeatureValue.create_from_video_frame(image_frame)
    binding.bind("data_0", image_feature_value)
    shape = winml.TensorFloat.create([1, 1000, 1, 1])
    binding.bind("softmaxout_1", shape)
    return (session, binding)