Exporting to Onnx with dynamic shapes

apache / mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

https://mxnet.apache.org

Apache License 2.0

20.77k stars 6.8k forks source link

Exporting to Onnx with dynamic shapes #19598

Open shroudie opened 3 years ago

shroudie commented 3 years ago

Description

I am not 100% sure but I think current API onnx_mxnet.export_model only supports exporting onnx model with fixed shape.

I know I can directly modify the onnx graph, but some models that I have failed to load after I modify the input and output batches. I was wondering if it is possible to have official feature for the API.

github-actions[bot] commented 3 years ago

Welcome to Apache MXNet (incubating)! We are on a mission to democratize AI, and we are glad that you are contributing to it by opening this issue. Please make sure to include all the relevant context, and one of the @apache/mxnet-committers will be here shortly. If you are interested in contributing to our project, let us know! Also, be sure to check out our guide on contributing to MXNet and our development guides wiki.