Gst_parse_error: no element "hailonet" (1)

General
1

Hi,

I tried to go to 4.18 on the raspberry pi5 with hailo 8l.
Device is recognized however trying to run the detetion.py script on
a video I get the error in the subject. I did an git pull on August 3rd before running it. Any clues how to get this working?

BR,

Konstantin

2

I am getting the same error after updating to to 4.18.

3

I completely wiped the SD card got back to 4.17 so at least the examples for the rpi-github rebo are working again.

I wonder when there will be a working version of 4.18 that would also allow to use the board from python without GST.

5

Hey,

We are currently working with Raspberry to ensure the new updates are available on the apt server. They will be accessible soon.

If you prefer to install it manually, please follow these steps:

  1. Remove all Hailo-related files from your Raspberry Pi.
  2. Install the 4.18 PCIe driver.
  3. Install HailoRT 4.18.
  4. Open a virtual environment and install PyHailoRT.

For more information, you can check out the guides in the Hailo Developer Zone.

Additionally, you might find these community posts helpful:

Best regards,

6

Will the rpi-example code work if I follow this procedure?

7

Yes , You can also run the Hailo Python API.

8

The rpi example code does not run despite following step 1 - 4 mentioned because hailonet was not found.
When I tried verifying with “gst-inspect-1.0 hailo” the error was “No such element or plugin ‘hailo’”.

9

I did the same thing on my raspberry pi 5 and got the same error message again. I can only get it to work on the older version 4.17.

10

Hello @huqkazanx,

If you haven’t installed version 4.17, you’ll need to install the Tappas core separately. This is because the Tappas core is typically included within the hailo-all installation package for version 4.17 and above.

11

Hey @davidr99

What error did you get ?

12

I am getting this:

gst-inspect-1.0 hailo

No such element or plugin ‘hailo’

I do have tappas-core installed:
sudo apt list | grep tappas

hailo-tappas-core-3.28.2/stable,now 3.28.2 arm64 [installed]

13

So I was able to get this working by downloading and installing GitHub - hailo-ai/tappas: High-performance, optimized pre-trained template AI application pipelines for systems using Hailo devices

I did run into issues trying to compile it with the rpi5 flag, so I ended up editing the install.sh file and editing the line with:

python3 $TAPPAS_WORKSPACE/downloader/main.py $target_platform
to be
python3 $TAPPAS_WORKSPACE/downloader/main.py rpi

That did work for me once I did that. Now I just need to do a source to get it all working.

source /home/pi/.hailo/tappas/tappas_env

This may be fixed if anyone is reading this in the future, or maybe I messed something else up.

1 Like