glow: [ONNXModelLoader] Support for LogSoftmax operator is missing

Tried compiling a ONNX model containing LogSoftmax operator and the compiler is failing with this error:

Error code: MODEL_LOADER_UNSUPPORTED_OPERATOR
Error message: Failed to load operator LogSoftmax .
Error return stack:
/workspaces/pytorch-glow/glow/lib/Importer/ONNXModelLoader.cpp:3745
/workspaces/pytorch-glow/glow/lib/Importer/ONNXModelLoader.cpp:3820
/workspaces/pytorch-glow/glow/lib/Importer/ONNXModelLoader.cpp:3949
/workspaces/pytorch-glow/glow/lib/Importer/ONNXModelLoader.cpp:3963
*** Check failure stack trace: ***

The glow version is at: ‘’’ commit e19f525b6e1bc91e04b79b55a80d7ed786faad7f Date: Thu Apr 2 18:21:35 2020 -0700 ‘’’

Running the following command line:

./build/bin/model-compiler -model=./mymodel.onnx -emit-bundle=./output -backend=CPU

About this issue

Original URL
State: open
Created 4 years ago
Comments: 16 (9 by maintainers)

Commits related to this issue

Support LogSoftmax from ONNX format (#5643) Summary: Support LogSoftmax operator in ONNX model loader. Since the node for LogSoftmax and corresponding lowering already exist in Glow, this PR only cha... — committed to pytorch/glow by Lewuathe 3 years ago

Most upvoted comments

@muhdmud You can find some general guidelines here. The main steps would be in this case:

You should define a new node LogSoftmax and define a lowering logic here to decompose it into Log + Softmax which are already supported by Glow.
Add logic in ONNXModelLoader to load a LogSoftmax node based on the proto description.
Add some unit tests in OnnxImporterTest

mciprian13 on Aug 7, 2020

Hi all, any updates on this? would like to help out

admud on Aug 5, 2020

@jfix71 I really wish but I am new to C++, so it would take me longer to get started. Otherwise I am happy to contribute.

antimora on Apr 9, 2020