tensorrt_l2norm_helper

tensorrt_l2norm_helper copied to clipboard

Loading engine file with Python

2

Hi, I have successfully used your tools to create a tensorrt engine and I'm trying to load the engine file with Python but the plugin is not found. I'm using:...

elisabetta496

../rtSafe/safeRuntime.cpp (25) - Cuda Error in allocate: 2 (out of memory)

1

Hi @r7vme, I have Implemented Two Custom Plugins(Einsum and RoIAlign). For FP32 it is working fine during ONNX to TensorRT Conversion using the command: ./trtexec --onnx=slow_fast_1.onnx --shapes=input1:1x3x8x256x455,input2:1x3x32x256x455,input3:1x5 --plugins=Einsum_op.so --plugins=RoI_Align.so --saveEngine=slow_fast_FP32.trt....

Darshcg

``` | ^~~~~~~~~ /home/jupyter/walmart/base/core/tensorrt_l2norm_helper/trt_l2norm_helper/l2norm_helper.cpp: In member function ‘virtual nvinfer1::IPluginV2* L2NormHelperPluginCreator::deserializePlugin(const char*, const void*, size_t)’: /home/jupyter/walmart/base/core/tensorrt_l2norm_helper/trt_l2norm_helper/l2norm_helper.cpp:205:66: error: invalid new-expression of abstract class type ‘L2NormHelper’ 205 | L2NormHelper* obj = new L2NormHelper(serialData,...

immuno121