[TVM Discuss] [Questions] Matrix size less than VTA block size

2020-08-26 Thread zhang hao (4paradigm) via TVM Discuss
Hi @thierry, is the feature supported already? --- [Visit Topic](https://discuss.tvm.ai/t/matrix-size-less-than-vta-block-size/3894/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/un

[TVM Discuss] [Questions] WARNING:root:Use native layout for depthwise convolution on NNVM

2020-08-26 Thread james_bond via TVM Discuss
I am trying to optimize my mobilenet based model. Using the default auto tune i am able to export but i am getting this warning. Is there further optimization possible ? Can you please suggest what changes i need to make in the script to this possible. --- [Visit Topic](https://discuss.t

[TVM Discuss] [Questions] Question about Conv1D support

2020-08-26 Thread wwwwcu via TVM Discuss
Have you support Conv1D operator? Could you share the code? Thx!! --- [Visit Topic](https://discuss.tvm.ai/t/question-about-conv1d-support/3635/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.

[TVM Discuss] [Questions] [BYOC] Codegen, JSON, non-composite

2020-08-26 Thread Max Sponner via TVM Discuss
Thank you, but I have got another question: Is there a way to actually see the raw JSON output, that has been generated by the backend easily? --- [Visit Topic](https://discuss.tvm.ai/t/byoc-codegen-json-non-composite/7719/3) to respond. You are receiving this because you enabled mailing

[TVM Discuss] [Questions] [Auto-TVM] How to Auto tune the model on iOS device

2020-08-26 Thread Dileep via TVM Discuss
Hi @kazum, @tqchen Thank you for the response. I followed the above link to connect the proxy on iOS device able to connect the RPC Proxy. but i went through some of the tutorials , before tune the model we need to start the RPC tracker (https://tvm.apache.org/docs/tutorials/autotvm/tune_rela