I’m porting CenterNet https://github.com/xingyizhou/CenterNet to TensorRT. Im using C++ API and implementing plugin for deformable convolution layer.
On last layer I’ve got
../builder/cudnnBuilderGraph.cpp (660) - Assertion Error in checkSanity: 0 (tensors.size() == g.tensors.size())
I thought that it might be shape mismatch, but on defining network it doesn’t assert, only on engine building.
This error shows up on IElementWiseLayer. It concatenates previously computed tensor with deconvoled tensor. If remove IElementWiseLayer engine will be formed without errors. In PyTorch it corresponds to this line https://github.com/xingyizhou/CenterNet/blob/master/src/lib/models/networks/pose_dla_dcn.py#L477
Can I send project so you can check what is wrong? (I can’t publicly publish code)
Graphical cards on which was tested:
- GeForce 1050Ti (Ubuntu 16.04, CUDA 10.1, TensorRT 220.127.116.11)
- Tesla K80 (CentOS7, CUDA 10.1, TensorRT 18.104.22.168)
- Tesla P100 (Ubuntu 16.04, CUDA 10.0, TensorRT 22.214.171.124)
Here is log - https://gist.github.com/blacksailer/ba795610cedca5747271da6698b7b994