Matt Strong

I also get an error of `[TensorRT] ERROR: (Unnamed Layer* 1033) [ElementWise]: elementwise inputs must have same dimensions or follow broadcast rules (input dimensions were [1,256,2,2] and [1,2,2,76]).` Are the...

Hi, no. I am using https://github.com/onnx/onnx-tensorrt

I didn't have to do that much work for conversion.

@250898 could you maybe say the specific steps/commands that you did?

@valeria025 Can you give a more detailed description of the problem?

Hi, do you have OpenCV installed? I had a similar error. @guytenn

I agree, it might be good to have the method as "expected" by default There was a small bug where expected depth wasn't previously used in `depth-nerfacto`: https://github.com/nerfstudio-project/nerfstudio/pull/2852/files

@BIGWangYuDong pinging for visibility.