ros_deep_learning
ros_deep_learning copied to clipboard
dusty-nv
Deep learning inference nodes for ROS / ROS2 with support for NVIDIA Jetson and TensorRT
Hi when i listen to the topic /detectnet/detections I get this output: header: seq: 35942 stamp: secs: 1711107077 nsecs: 727951291 frame_id: '' detections: - header: seq: 0 stamp: secs: 0...
**Description:** I am experiencing a significant performance drop when running the mobilenet-ssd-v2 model with a detectnet ROS node compared to standalone execution. The FPS drops by approximately two-thirds, which is...
I have a custom node to receive the outgoing detections topic and would like to display the detection IDs and confidence. I was able to output hypothesis.class_id and .score to...
Hello, I manage to use ros_deep_learing with ros2 foxy using a usb camera (by the way, is it normal that I get 9 fps on average instead of 45 fps...
I am trying to use the video-output node to stream an image topic to QGroundControl using RTSP, but keep getting error messages like "streaming stopped, reason not-linked (-1)". I have...
Hi, I'm using segnet to load a custom segmentation network and I was wondering if I can change precision to fp32? Currently I am getting this when i run it...
Hi @dusty-nv , Thank you for this amazing project. I am trying to use a re-trained YOLOV8 model (re-trained using [Ultralytics](https://github.com/ultralytics) Library on [VisDrone Dataset](https://github.com/VisDrone/VisDrone-Dataset)) in onnx format with your...
``` ~/jetson-inference$ docker/run.sh --ros=noetic ARCH: aarch64 reading L4T version from /etc/nv_tegra_release L4T BSP Version: L4T R35.4.1 [sudo] password for nrover: localuser:root being added to access control list CONTAINER_IMAGE: dustynv/ros:noetic-pytorch-l4t-r35.4.1 ROS_DISTRO:...
I add a sensor_msgs::CameraInfo publisher to manage calibration file It works on ROS1 only.
