TensorRT memory consumption

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

I try to build YOLO11 segmentation engine with TensorRT 10.3.0.

I always receive error messages:

[TRT] /1/Reshape_10: IShuffleLayer with zeroIsPlaceHolder=true has reshape dimension at position 1 that might or might not be zero. TensorRT resolves it at runtime, but this may cause excessive memory consumption and is usually a sign of a bug in the network.

How to fix it?

4

Hi @June.Lin ,

This was a known bug in old release,

Would request you to pls try the latest, which should resolve the error.

Thanks