[Apache TVM Discuss] [Questions] How to modify and add an operator in pytorch frontend

[tang Iverson via Apache TVM Discuss <no...@discuss.tvm.ai>]

@masahi Thank you for answering the question **https://github.com/apache/incubator-tvm/issues/6761**

I also want to ask if it is difficult to modify the underlying implementation of **max pool op** to support **recording maximum index**? Does tvm have a specific example code for adding an operator in pytorch frontend?





---
[Visit Topic](https://discuss.tvm.apache.org/t/how-to-modify-and-add-an-operator-in-pytorch-frontend/8313/1) 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/unsubscribe/16b14a84e538773d9b6f9df8a7d30d03dc6d9a7022eb681a5bcee36b75d4f85b).

[Apache TVM Discuss] [Questions] How to modify and add an operator in pytorch frontend

[masahi via Apache TVM Discuss <no...@discuss.tvm.ai>]

We have many examples for operator conversion in frontend/pytorch.py.

I don't recommend modifying the max pool implementation. TVM doesn't take into account the indices from max pool, so you need to modify code everywhere.





---
[Visit Topic](https://discuss.tvm.apache.org/t/how-to-modify-and-add-an-operator-in-pytorch-frontend/8313/2) 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/unsubscribe/eff98cda80997c80020b5b11a291bae9a55adad5ab7f3bcb826ddaea4c776fd4).