Hi Pete,
I have a similar issue and I don't know how to resolve it. Would you mind
explain in detail? How to convert Keras model from sequential to functional?
Thanks in advance.
---
[Visit
Topic](https://discuss.tvm.ai/t/incompletetypenode-cannot-resolve-type-of-var/3594/4)
to respond.
Is there any one can help? Thanks in advance.
---
[Visit
Topic](https://discuss.tvm.ai/t/will-tvm-be-compiled-as-a-standalone-c-library/6607/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai
Use implementation for op not is_dyn: nn.dense
inputs size: 2
data input shape: [1, 512]
weight input shape: [1000, 512]
local_pyfunc:
WARNING:strategy:dense is not optimized for this platform.
local_pyfunc:
data input is NHWC, How is the weight input setted to NHWC?
---
[Visit
Topic](ht
@comaniac Your solution works great! Thanks for the explanation.
---
[Visit
Topic](https://discuss.tvm.ai/t/how-to-reset-relay-to-use-the-default-config/6642/3)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https
This is a tricky question. Theoretically you only need to build the module
again without `apply_history_best` and measure its latency. However, if you
build the same module twice, the compiler engine will use the previous built
programs to reduce the build time in the second time. This can be
Is there a way to reset Relay to use the default configurations? I want to
compare the performance of two tuned logs in one process, but after applying
autotvm.apply_history_best() for the first log, it also affect the second run.
Is there a way to revert the effect of apply_history_best()? Th
