Hello, We are working on a project that requires the use of the DriveNet. We are interested in to know where we can find the type of input that this DNN requires and also the output that we can get after infer an image. We saw that we get an image with a Bounding Box in some kinds of objects but how we can extract this information in “text format” and also, which is all the information that we can extract from DriveNet?
Another interesting think to know, there is any information to transform an image in ROS2 using sensor_msgs/Image in a CUDA image?
Thanks in advance!
NVIDIA DRIVE™ Software 10.0 (Linux)
Target Operating System
NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
SDK Manager Version
Host Machine Version
native Ubuntu 18.04