Comments (15)
@EhrazImam I think this problem is related to the YAML file, please check YAML file is not corrupted
from vins-fusion-gpu-tx2-nano.
Hi @arjunskumar thanx for your quick reply
i solved it but how can i use d435i when i am running its to slow
from vins-fusion-gpu-tx2-nano.
enord@enord:~$ rosrun vins vins_node /home/enord/catkin_ws/src/VINS-Fusion-gpu/config/realsense_d435i/realsense_stereo_imu_config.yaml
[ INFO] [1636018928.744714982]: init begins
config_file: /home/enord/catkin_ws/src/VINS-Fusion-gpu/config/realsense_d435i/realsense_stereo_imu_config.yaml
USE_IMU: 1
IMU_TOPIC: /camera/imu
result path /home/enord/output//vio.csv
[ WARN] [1636018929.790541478]: Optimize extrinsic param around initial guess!
camera number 2
[ INFO] [1636018929.834734587]: Unsynchronized sensors, online estimate time offset, initial td: 0
[ INFO] [1636018929.834885147]: ROW: 480 COL: 640
exitrinsic cam 0
1 0 0
0 1 0
0 0 1
-0.00552 0.0051 0.01174
exitrinsic cam 1
1 0 0
0 1 0
0 0 1
0.0446571 0.0051 0.01174
set g 0 0 9.805
[ INFO] [1636018929.836644419]: reading paramerter of camera /home/enord/catkin_ws/src/VINS-Fusion-gpu/config/realsense_d435i/left.yaml
[ INFO] [1636018929.837479622]: reading paramerter of camera /home/enord/catkin_ws/src/VINS-Fusion-gpu/config/realsense_d435i/right.yaml
MULTIPLE_THREAD is 1
[ WARN] [1636018929.838289161]: waiting for image and imu...
OpenCV(3.4.1) Error: Gpu API call (invalid device symbol) in linearRow, file /home/enord/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp, line 365
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(3.4.1) /home/enord/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp:365: error: (-217) invalid device symbol in function linearRow
Aborted (core dumped)
from vins-fusion-gpu-tx2-nano.
can you share your yaml file through which you are using gpu
here is mine
%YAML:1.0
#common parameters
#support: 1 imu 1 cam; 1 imu 2 cam: 2 cam;
imu: 1
num_of_cam: 2
imu_topic: "/camera/imu"
image0_topic: "/camera/infra1/image_rect_raw"
image1_topic: "/camera/infra2/image_rect_raw"
output_path: "/home/enord/output/"
cam0_calib: "left.yaml"
cam1_calib: "right.yaml"
image_width: 640
image_height: 480
Extrinsic parameter between IMU and Camera.
estimate_extrinsic: 1 # 0 Have an accurate extrinsic parameters. We will trust the following imu^R_cam, imu^T_cam, don't change it.
# 1 Have an initial guess about extrinsic parameters. We will optimize around your initial guess.
body_T_cam0: !!opencv-matrix
rows: 4
cols: 4
dt: d
data: [ 1, 0, 0, -0.00552,
0, 1, 0, 0.0051,
0, 0, 1, 0.01174,
0, 0, 0, 1 ]
body_T_cam1: !!opencv-matrix
rows: 4
cols: 4
dt: d
data: [ 1, 0, 0, 0.0446571,
0, 1, 0, 0.0051,
0, 0, 1, 0.01174,
0, 0, 0, 1 ]
#Multiple thread support
multiple_thread: 1
#Gpu accleration support
use_gpu: 1
use_gpu_acc_flow: 1
#feature traker paprameters
max_cnt: 150 # max feature number in feature tracking
min_dist: 30 # min distance between two features
freq: 10 # frequence (Hz) of publish tracking result. At least 10Hz for good estimation. If set 0, the frequence will be same as raw image
F_threshold: 1.0 # ransac threshold (pixel)
show_track: 1 # publish tracking image as topic
flow_back: 1 # perform forward and backward optical flow to improve feature tracking accuracy
#optimization parameters
max_solver_time: 0.04 # max solver itration time (ms), to guarantee real time
max_num_iterations: 8 # max solver itrations, to guarantee real time
keyframe_parallax: 10.0 # keyframe selection threshold (pixel)
#imu parameters The more accurate parameters you provide, the better performance
acc_n: 0.1 # accelerometer measurement noise standard deviation. #0.2 0.04
gyr_n: 0.01 # gyroscope measurement noise standard deviation. #0.05 0.004
acc_w: 0.001 # accelerometer bias random work noise standard deviation. #0.002
gyr_w: 0.0001 # gyroscope bias random work noise standard deviation. #4.0e-5
g_norm: 9.805 # gravity magnitude
#unsynchronization parameters
estimate_td: 1 # online estimate time offset between camera and imu
td: 0.00 # initial value of time offset. unit: s. readed image clock + td = real image clock (IMU clock)
#loop closure parameters
load_previous_pose_graph: 0 # load and reuse previous pose graph; load from 'pose_graph_save_path'
pose_graph_save_path: "/home/enord/output/pose_graph/" # save and load path
save_image: 1 # save image in pose graph for visualization prupose; you can close this function by setting 0
from vins-fusion-gpu-tx2-nano.
ones i make it run using cpu its just gave me a photo and after that its stuck
from vins-fusion-gpu-tx2-nano.
I am trying to use vins fusion gpu on jetson xavier nx with D435i
when i am running it, after few seconds its stop working.
basically its crash and not showing up any error.
from vins-fusion-gpu-tx2-nano.
@EhrazImam Hey I'm sorry, I dont have access to jetson platforms. Have you fixed the issue?
from vins-fusion-gpu-tx2-nano.
@EhrazImam Have you fixed the issue? I meet the same wrong.
from vins-fusion-gpu-tx2-nano.
@z1047941150 can you check usb doesn't turn off in power saving mode
from vins-fusion-gpu-tx2-nano.
@arjunskumar
How to check it? I'm using 20w mode
from vins-fusion-gpu-tx2-nano.
@z1047941150 add usbcore.autosuspend=-1
in extlinux.conf
from vins-fusion-gpu-tx2-nano.
@arjunskumar I kown the reason, when complied Opencv3.4.1. We should turn gpu_arch=7.2 if we used Jetson NX.
from vins-fusion-gpu-tx2-nano.
@arjunskumar I kown the reason, when complied Opencv3.4.1. We should turn gpu_arch=7.2 if we used Jetson NX.
Hi, guy. I met the same problem with
OpenCV(3.4.1) Error: Gpu API call (invalid device symbol) in linearRow, file /home/tuboshu4/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp, line 365
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(3.4.1) /home/tuboshu4/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp:365: error: (-217) invalid device symbol in function linearRow
And I tried to complie opencv3.4.1 with -D CUDA_ARCH_BIN=7.2,and it did not work. It still show the same error. And my device is Nvidia NX with jetpack 4.4.1. cuda 10.2.89.
from vins-fusion-gpu-tx2-nano.
@arjunskumar I kown the reason, when complied Opencv3.4.1. We should turn gpu_arch=7.2 if we used Jetson NX.
Hi, guy. I met the same problem with OpenCV(3.4.1) Error: Gpu API call (invalid device symbol) in linearRow, file /home/tuboshu4/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp, line 365 terminate called after throwing an instance of 'cv::Exception' what(): OpenCV(3.4.1) /home/tuboshu4/opencv-3.4.1/modules/cudafilters/src/cuda/row_filter.hpp:365: error: (-217) invalid device symbol in function linearRow
And I tried to complie opencv3.4.1 with -D CUDA_ARCH_BIN=7.2,and it did not work. It still show the same error. And my device is Nvidia NX with jetpack 4.4.1. cuda 10.2.89.
I met the same problem. Have you fixed the issue? Thank you for your help!
from vins-fusion-gpu-tx2-nano.
@Dellaldd I am not sure if it is the same problem, I am using Jetson nano which is different from Jetson NX. I resolved for the same issue with building opencv cuda_arch_bin=5.3,6.2,7.2 instead of just using cuda_arch_bin=6.2. It takes twice time lapse, but found it worked just fine. I am not sure it would be the solution for Jetson NX as well, but hope it helps a bit:)
https://developer.nvidia.com/cuda-gpus
from vins-fusion-gpu-tx2-nano.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vins-fusion-gpu-tx2-nano.