-
Notifications
You must be signed in to change notification settings - Fork 6.7k
[v1.x] Update ONNX tutorial and doc #20253
Conversation
|
Hey @waytrue17 , Thanks for submitting the PR
CI supported jobs: [unix-cpu, clang, unix-gpu, edge, windows-gpu, windows-cpu, website, sanity, centos-cpu, centos-gpu, miscellaneous] Note: |
python/mxnet/onnx/README.md
Outdated
| By setting up optional flags in export_model API, users have the control of partially/fully dynamic shape input export. The flag `dynamic` is set to switch on dynamic shape input export, and `dynamic_input_shapes` is used to specify which dimensions are dynamic (None for dynamic shape). | ||
|
|
||
| ```python | ||
| # None indicating dynamic shape at a certain dimension |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
here the dynamic shape can also be something like ('batch', 'seq_length') i.e. using strings rather than None
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated the description
|
I think we might also touch on dynamic shapes in the tutorial as this is a very common use case e.g. different image sizes or sequence lengths. Also I think we can add a section to introduce onnx-simplifier as it can significantly simplify the onnx graph in many cases. CC the author of onnxsim @daquexian: we are releasing mx2onnx in the upcoming mxnet 1.9 release : ) |
Added dynamic shape input in the tutorial, and a link reference to onnx-simp |
Zha0q1
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
Description
Update ONNX tutorial and doc
Checklist
Essentials
Changes
Comments