Skip to content

SwinUNETR for TensorRT #5893

@tangy5

Description

@tangy5

Current SwinUNETR is not scriptable by torch.jit.script, several features has some limitations to make SwinUNETR compatible with TensorRT.

This issue can discuss the potential solution for making SwinUENTR support TensorRT.

A potential solution is to make a 'light' version of this network, so we won't significantly impact users with a transition.

  • checkpoint option can be removed, as inference pipleline is mostly used and do not require checkpointing.
  • some packages such as itertools, einops needs to replaced.
  • Functions not scriptable such as Slice() need to be rewrite.

Forward functions that contains none basic python can be modified to support torch.jit.script.
A light version of SwinUNETR can be a subclass of current SwinUENTR network, when users uses SwinUNETR from bundle, it uses the light version which works with TensorRT.
The light version SwinUNETR need to be tested and evaluated for comparable performance to the current version.

Welcome comment on other options. There can be a better choice.

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Type

No type

Projects

Status

✅ Done

Relationships

None yet

Development

No branches or pull requests

Issue actions