V
Hi @Moderator, @modaltb
Any update on the configuration of tracking camera in HW Sensor ID- 3. Camera Server crashes whenever i connect tracking camera in HW sensor ID-3 (J7U) but in the camera server configuration, SDK 1.0 (C-06, C-14 , C-16, C-17 ) configurations shows that the tracking camera is connected to J7U.
Can you please give me update on this?
@James-Strawson Thanks for reply, Will look into it and get back.
Hi @modaltb, @Chad-Sweet
We are facing issue with our own tflite model deployed on voxl2 for text detection bounding boxes.
Here we are seeing "Failed to apply GPU deligate".
From our understanding it seems that model will run on CPU in this case. So we are seeing high inference latency of 7-8 seconds, which we want to minimize by running it on GPU.
Can you please help use with this issue.
PS: Our tflite model size is 41MB.
Attaching snapshot from voxl2 run for reference.
Thanks
Found the offset
its gpiochip1100
so for gpio 12
echo 1112 > /sys/class/gpio/export
will enable gpio 12
Hi,
I would like to access the gpio pin 12 using interposer M0076 TP5 at J8
echo 12 > /sys/class/gpio/export
Not works shows Invalid argument
but
echo 1073 > /sys/class/gpio/export
works
But in voxl2 the numbering is different starts at 1072 and ends at 1280
gpiochip1100 has 180 in ngpio
how to get exact number for gpio pin 12 in relation to above.
can someone tell the mapping of gpio numbers.
@Chad-Sweet Thanks for reply,
I am just triggering via python subprocess
voxl-send-command hires_snapshot snapshot
able to get snapshots.
will try to look into mavsdk also.
Hi,
Can anyone help me how to take snapshots using hires_snapshot feature in python script in voxl2. I am able to see /hires_snapshot topic in ros but unable to process through it.
@Jyotish-Kumar i have faced the same issue. the record pipe name has changed in dev branch, try to use
hires_large_encoded or hires_small_encoded based on your resolution requirement. Can find more config parameters in /etc/modalai/voxl-camera-server.conf