Hi @thkim
Did you check if your bit file is at
`/home/taeho/.vta_cache/pynq/0_0_1/1x16_i8w8a32_15_15_18_17.bit"`?
In my case, I copy the bit file to the above dir.
I also use `sudo` to run tracker
```
pushd apps/vta_rpc
sudo -E ./start_rpc_server_to_tracker.sh
popd
```
---
[Visit
Topic]
Hi @thkim
If you update your from the above [githhub
link](https://github.com/i24361/incubator-tvm/blob/0472b1f347976229a29be8a6e60b626a0604c8df/vta/tutorials/autotvm/tune_relay_vta_with_one_board.py)
and my change on the `export_library`, then let me check few more.
It is not a connection is
Figured it out.
Instead of `save`, which is likely due to the API changes over time,
`export_library` works
So here is the change and it works.
```
# Export library
print("Upload...")
#temp = utils.tempdir()
#lib.save(temp.relpath("graphlib.o"))
#remote.u
@hht
Thank you for your answer.
I used your code except uncomment the `return` so that I can tune.
It failed after the tune is done at ` lib.save(temp.relpath("graphlib.o"))`
https://github.com/i24361/incubator-tvm/blob/0472b1f347976229a29be8a6e60b626a0604c8df/vta/tutorials/autotvm/tune_relay_vt
@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, 1
@hht
Thank you so much, this fixed my issue.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/vta-workaround-for-autotuning-with-one-pynq-z1-board/8091/5)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://
