Currently, I try to learn and understand TVM. I have a mxnet model and I want
to do AutoTVM, so I try to use `autotvm.task.extract_from_program`. The code is
similar to this
```
target = tvm.target.cuda()
tasks = autotvm.task.extract_from_program(
mod["main"], target=target, target_host
I'm not sure about executor class.
However, this method might work on your requirement too. (never run it, but
from my guess it should work too)
```
mod, params = relay.frontend.from_onnx(onnx_model, shape_dict)
func = mod["main"]
target = "llvm"
with tvm.transform.PassContext(opt_level=3):
Hello, @fantasyRqg
Thanks for very good PR!! I try using your code to export one system-lib model
and I have one problem about model similarity score.
I try to export 2 model with `build_one_system_lib` and it work fine. However,
when I try to validate similarity score between exported TVM m
Hi! Do you have update on this topic? Do you solve problem?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-build-libtvm-runtime-so-for-armeabi-v7a-or-arm64-v8a/5885/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [
Currently, I try to export static android system-lib model. I set target to
```
target = 'opencl -device=mali --system-lib'
target_host = 'llvm -device=arm_cpu -mtriple=arm64-linux-android --system-lib'
```
and I export by
```
lib.export_library('model.tar', ndk.create_shared) # come from tvm.
@sosa3104 Good to know! Thank you too!!
---
[Visit Topic](https://discuss.tvm.apache.org/t/tvm-deploy-a-c-example/9027/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/email/unsubscr
Thank you very much! I will check the PR that you send to me.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-can-i-get-output-name-from-graph-runtime/8479/3)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](
I read the docs and have a question about how can we know what is the output we
get from graph runtime.
For example, I have model A that have 3 outputs.
The 3 outputs is
1) name: LayerA, shape: (1, 100)
2) name: LayerB, shape: (1, 100)
3) name: LayerC, shape: (1, 100, 200)
I see the this fu
