pycuda._driver.LogicError: cuMemcpyHtoDAsync failed: invalid argument

[dexception]

Yolov3-tiny 416 the default model with the default cfg file.

Traceback (most recent call last):
  File "onnx_to_tensorrt.py", line 228, in <module>
    main()
  File "onnx_to_tensorrt.py", line 202, in main
    trt_outputs = common.do_inference(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream, batch_size=batch_size)
  File "/opt/github/yolov3-tiny-onnx-TensorRT/common.py", line 145, in do_inference
    [cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
  File "/opt/github/yolov3-tiny-onnx-TensorRT/common.py", line 145, in <listcomp>
    [cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
pycuda._driver.LogicError: cuMemcpyHtoDAsync failed: invalid argument