You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by ximing via TVM Discuss <no...@discuss.tvm.ai> on 2020/05/12 07:00:32 UTC
[TVM Discuss] [Questions] "Concat" node has no "topi" key when auto
tuning onnx model to tvm
Encounter a "KeyError:'topi_op'" problem when running tvm auto tune.
It occurs in _iterate_layout_transform() when running DPTuner.benchmark_layout_trasform.
![image|690x390](upload://18IiODhnGN9nE2cypgjRq8mUMkK.png)
As you see, in_node_entry[964] has no key "topi_op", this node is the second(last) "concat"node in the model pic below.
Actually the question is why this "concat" node(in_node_entry[964]) has multipe inputs(two slice inputs and add), but not become a valid node with "topi_op"and "workloads" ?
---
[Visit Topic](https://discuss.tvm.ai/t/concat-node-has-no-topi-key-when-auto-tuning-onnx-model-to-tvm/6651/1) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/693930fa400f9c5cff663e49bae3dd740eaef98188fcf66ea72c1c18a92e125e).
[TVM Discuss] [Questions] "Concat" node has no "topi" key when auto
tuning onnx model to tvm
Posted by ximing via TVM Discuss <no...@discuss.tvm.ai>.
The model pic is here:
![image|100x500](upload://qVZUbw2XPNwwvYB6GEJKfBkmfMI.png)
---
[Visit Topic](https://discuss.tvm.ai/t/concat-node-has-no-topi-key-when-auto-tuning-onnx-model-to-tvm/6651/2) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/37b3a14f77127d8e1d86c7586af1a510f68cb09c69082705bed10862305a1c26).