Chao Zhang

Hmm after investigating this a bit, this might be trickier than I thought. Specifically, [dynamic shapes in TRT](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#work_dynamic_shapes) don't work as how I had envisioned it: > Specify each runtime...

Alright, I think I've got _something_ working with respect to dynamic shapes. Turns out it was actually _easier_ than I had originally thought, although it took some experimentation as I...

Addressed in #743

I'm getting: ``` [06/07/2022-17:14:33] [TRT] [E] 7: [shapeMachine.cpp::execute::688] Error Code 7: Internal Error (IShuffleLayer:0:SHUFFLE:GPU: reshaping failed for tensor: (Unnamed Layer* 13) [Pooling]_outputreshape would change volume Instruction: RESHAPE_ZERO_IS_PLACEHOLDER{1 256 6 6}...

@mkulariya Just checking, but when you're performing the model conversion you are also supplying tensors of batch size 4 correct? And the above patch did not address your issue?

@mkulariya If you're using an older version of torch2trt then this might be a different issue than the one posted here. What version of torch2trt are you using? This issue...

#743 WIP PR addressing this issue

@sleepLion99 I tried running your above script but encountered the following error (on both master and on my PR): ``` Loaded pretrained weights for efficientnet-b4 [06/28/2022-00:25:52] [TRT] [I] [MemUsageChange] Init...

This is likely the same issue presented in #247.

I'll post a solution shortly. I believe the following should work: We should be able to convert `slices` into a `tuple` if it is not already one, and consume that...