I know that TensorRT 3RC has a version for Jetson platforms, but given that the PX2 has TX2s, will TensorRT work on it?
I tried building the samples, but it gives the following errors (even though I have libcudnn.so.7).
/usr/bin/ld: skipping incompatible /usr/local/cuda/lib64/libcudnn.so when searching for -lcudnn
usr/bin/ld: warning: libcudnn.so.7, needed by …/…/lib/libnvinfer.so, not found (try using -rpath or -rpath-link)
Do you have an ETA? Given that one of the applications that could really use optimized inference is autonomous driving using your embedded hardware, I was hoping it would be announced by this year’s GTC in Munich.