[VTA] Workaround for Autotuning with One PYNQ Z1 Board

@hht

I got the the tutorial working; however, it failed after the tune. Have you see this error?

Thank you,

$ python3 ./tune_relay_vta_one_board.py 
Extract tasks...
Extracted 10 conv2d tasks:
(1, 14, 14, 256, 512, 1, 1, 0, 0, 2, 2)
(1, 28, 28, 128, 256, 1, 1, 0, 0, 2, 2)
(1, 56, 56, 64, 128, 1, 1, 0, 0, 2, 2)
(1, 56, 56, 64, 64, 3, 3, 1, 1, 1, 1)
(1, 28, 28, 128, 128, 3, 3, 1, 1, 1, 1)
(1, 56, 56, 64, 128, 3, 3, 1, 1, 2, 2)
(1, 14, 14, 256, 256, 3, 3, 1, 1, 1, 1)
(1, 28, 28, 128, 256, 3, 3, 1, 1, 2, 2)
(1, 7, 7, 512, 512, 3, 3, 1, 1, 1, 1)
(1, 14, 14, 256, 512, 3, 3, 1, 1, 2, 2)
Tuning...
[Task 10/10]  Current/Best:    4.91/  22.07 GFLOPS | Progress: (100/100) | 83.85 sCompile...

Upload...
Traceback (most recent call last):
  File "./tune_relay_vta_one_board.py", line 457, in <module>
    tune_and_evaluate(tuning_option)
  File "./tune_relay_vta_one_board.py", line 432, in tune_and_evaluate
    temp = utils.tempdir()
AttributeError: 'GraphRuntimeFactoryModule' object has no attribute 'save'

So it failed at lib.save(temp.relpath("graphlib.o")).