Support Elu
operator, reading axes list from inputs rather than attribute in Reduce*
ops
#132
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This addresses a few issues I found while playing around with ONNX models from openpilot:
Elu
activation operatorReduce*
operators takeaxes
as a dynamic input rather than static attribute.ort-infer.py
script to run with models that havefloat16
inputsFor RTen, the original
supercombo.onnx
model fails to convert because the weights are in float16 format. However this hack works (at least for getting the model to run, I haven't verified the outputs):TODO:
Reduce
operator change