Nick Comly
Nick Comly
cc: @gs-olive
Hi @QiusongYang can you please provide your python script where you are seeing this failure? Without knowing the specific failure we won't be able to help debug with you.
As @narendasan mentioned, this is a limitation of Torchscript itself. If you need the model to be run in Torchscript, please file an issue to [pytorch/pytorch](https://github.com/pytorch/pytorch/issues). Alternatively, in v1.2 Torch-TRT...
Bump @narendasan ^
Resolved by #1140. Closing
Closing based on [#1096 (comment)](https://github.com/pytorch/TensorRT/issues/1096#issuecomment-1213452229). Please comment if this is not resolved.
Comment added by Nick Comly in Aha! - [View](https://nvaiinfra.aha.io/comments/6987510486128889325) May slip to v0.5.0, if so then push to Master and customer can get it earlier
Hi @ntakouris have you checked out the [v1.2 release](https://github.com/pytorch/TensorRT/releases/tag/v1.2.0)? It includes a first pass on collections (list & tuple I/O). @narendasan is this issue OK to close?
We are in the process of supporting Detectron2 OD networks. We will updated when there is a concrete timeline.
@dheerajperi FYI on dynamic shape + resize.