Gaze Estimation: Output File saving with Meta Data

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

i have been working on gaze estimation model, so i have completely configure everything and have been testing it on image and videos, and having some output, however i would like to save the output in my local directory, but im not sure which files need to be edit and what to add to get the output (image or video with its meta data on it), so kindly guide me as quick as you can to how thing should be proceed from here:

here is the sample of the output:

Frame Number = 922 Face Count = 1
Outp thread 923 frame 0 source 2
Gaze execute
Gaze execute end
Gaze start meta add
Outp thread 923 frame 0 source 3
output push to downstream
CustomLib: OutputThread in_surf=0x7f958833f6f0, Pushing Frame 924 to downstream… flow_ret = 0 TS=0:00:30.766666359
Gaze: -263.750000 70.937500 -170.000000 -0.065613 0.102783
Frame Number = 923 Face Count = 1
End of stream
Returned, stopping playback
Average fps 9.821431
Totally 921 faces are inferred
Deleting pipeline

3

You can just set the output field in the config file. When you set the type: 1 and filename: test, it will generate the test.mp4 file in the current directory.

5

Thank you

6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.