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 Max Sponner via Apache TVM Discuss <no...@discuss.tvm.ai> on 2021/04/14 10:23:03 UTC

[Apache TVM Discuss] [Questions] Questions regarding relay.analysis.extract_fused_functions


I tried to get information about which functions have been fused in my compiled IRModule.

The network is a MXNet version of ResNet-18 and has been compiled with relay.build_module.build(mod, target, params=params).

When I list the functions of the IRModule, I get only a single function with 103 input arguments.
The output of relay.analysis.extract_fused_functions(mod) is a dictionary with 26 relay functions.
However, I do not understand what is being returned here.

The functions have a body, an op and a name. The names are usually "nn.relu", "nn.global_avg", and similar. Convolutional layers are not in there.

Is there a way to correspond these layers/groups with the PackedFunctions that are executed by the graph_executor? These usually have namens like "fused_nn_contrib_conv2d_NCHWc_add_add_nn_relu_4"





---
[Visit Topic](https://discuss.tvm.apache.org/t/questions-regarding-relay-analysis-extract-fused-functions/9700/1) 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/7fb17aad7573ecfc6fc64b3a2497ac7549f5180d8f22404136e2408c002d94da).