With TensorRT 7.0 comes compatibility with 3D convolution. But 8 bit integer quantization still isn’t available for 3D convolution, as shown here, section “Layer and precision” : https://docs.nvidia.com/deeplearning/sdk/tensorrt-support-matrix/index.html
However, it’s a huge part of performance gains.
In fact, we should be able to look at a 15 folds performance gain with TensorRT (based on what I obtain with 2D models on various hardware) whereas, with what is available right now, I could only obtain a *1.5 folds.
Are there plans to make the rest of TensorRT optimizations available for 3D convolution ?