run_model¶
dragon.vm.tensorrt.onnx.
run_model
(
model,
inputs,
device='CUDA:0',
**kwargs
)[source]¶Execute an onnx model once.
- Parameters:
- model (onnx.ModelProto) – The onnx model.
- inputs (Union[Sequence, Dict]) – The input arrays.
- device (str, optional) – The executing device.
- Returns:
namedtuple – The model outputs.