I am trying to run pelee on tx2 and use tensorrt acceleration, and I found this:https://github.com/cathy-kim/Pelee-TensorRT
So I deploy according to this project.
Since my tensorrt is 6.0,so I removed pelee_merged.caffemodel.cache and rerun
But it did not succeed.
The log shows:
pelee: nvPluginsLegacy.cpp:1026: virtual void nvinfer1::plugin::DetectionOutputLegacy::configure(const nvinfer1::Dims*, int, const nvinfer1::Dims*, int, int): Assertion `C2 == inputDims[param.inputOrder].d’ failed.
Aborted (core dumped)
This may be caused by different versions of tensorrt, mine is tensorrt6, but the original author was tensorrt4.
I looked for a lot, and I tried six combinations of “inputOrder=[0, 1, 2],” but it still didn’t work.
Please give my some hints for modification, Sincere thanks for you!!!