How to use command to do inference
YaoJiawei329 opened this issue · 0 comments
Hi, all. I am a newbie on ROS and deep learning, wonder how to use these params in /ros_deep_leraning/launch/imagenet.ros1.launch.
I just want to run a classification demo on a video(mp4) or a picture(jpg), resnet18. I tried this command
$ roslaunch ros_deep_learning imagenet.ros1.launch input:=file:///home/nvidia/test_videos/test.mp4 output:=file:///home/nvidia/test_result.mp4 model_name:=resnet18
but it turns out this error every try:
[ERROR] [1629873729.496301287]: [setParam] Failed to contact master at [localhost:11311]. Retrying...
(I had run $ roscore before it.)
I can correctly do inference in jetson-inference.
On Xavier, Jetpack 4.5, ROS melodic.
Can someone give me an example or tell me how to fix the ERROR. Thanks very much!