Hello! I encountered the following error while running onnx to tensorRT on Xavier
[TensorRT] WARNING: TensorRT was linked against cuDNN 8.0.2 but loaded cuDNN 8.0.0
[TensorRT] ERROR: ../builder/cudnnBuilderWeightConverters.cpp (541) - Misc Error in operator(): 1 (Weights are outside of fp16 range. A possible fix is to retrain the model with regularization to bring the magnitude of the weights down.)
[TensorRT] ERROR: ../builder/cudnnBuilderWeightConverters.cpp (541) - Misc Error in operator(): 1 (Weights are outside of fp16 range. A possible fix is to retrain the model with regularization to bring the magnitude of the weights down.)
ERROR: failed to build the TensorRT engine!
I would like to ask if you have relevant experience, and if retraining is the only solution?
Could this be related to my TensorRT or cuDNN version?
TensorRT version : 7.2.0
cuDNN version : 8.0.0
Hello! I encountered the following error while running onnx to tensorRT on Xavier
[TensorRT] WARNING: TensorRT was linked against cuDNN 8.0.2 but loaded cuDNN 8.0.0 [TensorRT] ERROR: ../builder/cudnnBuilderWeightConverters.cpp (541) - Misc Error in operator(): 1 (Weights are outside of fp16 range. A possible fix is to retrain the model with regularization to bring the magnitude of the weights down.) [TensorRT] ERROR: ../builder/cudnnBuilderWeightConverters.cpp (541) - Misc Error in operator(): 1 (Weights are outside of fp16 range. A possible fix is to retrain the model with regularization to bring the magnitude of the weights down.) ERROR: failed to build the TensorRT engine!
I would like to ask if you have relevant experience, and if retraining is the only solution? Could this be related to my TensorRT or cuDNN version? TensorRT version : 7.2.0 cuDNN version : 8.0.0