Still get different results.
I'm not familiar with relay, correct me if i make rookie mistakes. In my sample
code, `data` is input, `bias` & `weight` are params, so `m.set_input('data',
...)` is enough.
PS: I use `offset = relay.var("bias", ...)` instead of `offset =
relay.var("offset", ...)
The input name to `set_input` shouldn't be 0, 1 etc, but the corresponding
variable names like "data", "weight", "offset", "input0" etc. Can you try if
this change gets the correct output?
---
[Visit
Topic](https://discuss.tvm.ai/t/deformable-conv-implementations-differences-between-pyto
I'm trying to convert torchvision dcn to tvm dcn. However, with the same
inputs, i couldn't get same output from torchvision dcn and tvm dcn.
I tried 2 versions of pytorch dcn implementation, torchvision & mmcv, get the
sample outputs with the same inputs(data, offset, weight).
But, results f
We don’t support non-grid tuning space in AutoTVM. On the other hand, the new
auto-scheduler that is being upstreamed will support symbolic tuning parameters
with conditional expression.
---
[Visit
Topic](https://discuss.tvm.ai/t/how-to-define-search-space-an-bypass-some-of-them/7699/2)
Hi guys:
Do we have some functions which I can use to bypass some configurations in
pre-defined search space.
For instance, If I I have three parameters should be tuned *p1* ,*p2* , *p2*
Followed and auto-tuning tutorial, I should do something like
```
cfg.define_knob("p1", [1, 2, 4])
cfg.
Dear community people,
I have no problems with TVM running natively on Linux (and it works great!),
but now I'm forced to use TVM for delpoyment on Windows.
It looks like I'm missing something in my appempt to cross-compile, and
therefore kindly asking for a help please.
I've built llvm/clang
