onnx export support of dynamic_axes

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

onnx export support of dynamic_axes #18979

Open dxls168 opened 4 years ago

dxls168 commented 4 years ago

Torch.onnx.export function can use dynamic_axes parameter can support dynamic input. Screenshot from 2020-08-21 21-54-07

onnx_mxnet.export_model function input is fixed such as [(1,3,224,224)]. Screenshot from 2020-08-21 21-54-40 I really hope mxnet adds dynamic_axes function like pytorch.

github-actions[bot] commented 4 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.