frankvp

LOL conviently I had this error earlier today. I just kinda brute forced- tried reinstalling things and upgrading things - I didn't have a set thing that I remembered -sorry

Yeah thank you- these are exactly the type of scripts i'm looking for

[CMakeError.txt](https://github.com/NVIDIA/TensorRT/files/9329819/CMakeError.txt) [CmakeOutput.txt](https://github.com/NVIDIA/TensorRT/files/9329820/CmakeOutput.txt) Theres the 2 logs. Knock ya self out (figuratively ofc)

Alright thanks for letting me know. Ill look into it more.

yo @zerollzeng I got something working in colab. Sorry for the @ but I was just wondering. I got it installed (i think) on colab. But when I do import...

Also, !dpkg -l | grep TensorRT gives: ii graphsurgeon-tf 8.4.2-1+cuda11.6 amd64 GraphSurgeon for TensorRT package ii libnvinfer-bin 8.4.2-1+cuda11.6 amd64 TensorRT binaries ii libnvinfer-dev 8.4.2-1+cuda11.6 amd64 TensorRT development libraries and headers...

^Also does that mean I have the most recent version? The 8.4.2.1 thats infront of the +cuda11.6?

@zerollzeng can I make a new post saying something along the lines of Importing on colab and then give the script that I used? It might be useful for others?...

Alright, I'll give that a try and get back to you with the results so that we can go from there

Hi @azhurkevich , so I've run the export_onnx.py from detectron2 (which ran successfully) and I tried to use the create_onnx.py as you told me, but I'm getting an error. I've...