Not able to download generated files in ST Edge AI Developer Cloud

[athern27]

HI everyone,

I have recently bought a STM32N6570-DK and I am trying to follow this tutorial to try and implement an example model on my board. I am able to get results and good benchmark but when I go to Generate Your Project I am unable to download anything. It doesn't show any option to download the files. 

 

I believe it have been should be something shown like this in the video

Kindly help me in this regard.

 

[Julian E.]

Hello @athern27,

 

Indeed, because of the Export Control Classification Number (ECCN) imposed by the US, we don't have the right to deliver code for the N6 without a form.

For the moment we disabled the download on st edge ai cloud while waiting for a status concerning the ECCN.

 

To easily test the N6 and models I suggest you take a look at the ST Model ZOO:

GitHub - STMicroelectronics/stm32ai-modelzoo: AI Model Zoo for STM32 devices

 

The model zoo is divided into 2 github, one containing multiple architectures of models for multiple use case and the other containing the scripts to retrain, quantized, benchmark, deploy etc...

 

In your case, based on your model's name, you should take a look at the object detection part of the ST model zoo and the deployment run mode (stm32ai-modelzoo-services/object_detection/deployment/README.md at main · STMicroelectronics/stm32ai-modelzoo-services · GitHub)

 

To be able to deploy code to the N6, you will need to follow this documentation:

stm32ai-modelzoo-services/object_detection/deployment/README_STM32N6.md at main · STMicroelectronics/stm32ai-modelzoo-services · GitHub

(In short, you copy paste the getting started application into the model zoo folder for it to be capable of generating code. For the same reason as the dev cloud, we can't provide code via the model zoo. Only the getting started can be delivered thanks to the form.)

 

Furthermore, example code from the dev cloud is just an inference with a random input. Then it sends via serial some metrics, whereas the example code from the getting started + model zoo allows you to use the camera and display with your model.

 

Best regards

Julian

 

[athern27]

Thank you for a quick reply.

Can you please help me here. I followed the links you provided but when I run the following command from here.

 

 

python stm32ai_main.py --config-path ./config_file_examples/ --config-name deployment_n6_ssd_mobilenet_v2_fpnlite_config.yaml

 

 

I am getting this error. 

 

 

(st_zoo) kartikkhandewal@ATL-HPZG14-99:~/stm32packages/stm32ai-modelzoo-services/object_detection/src$ python3 stm32ai_main.py --config-path ./config_file_examples/ --config-name deployment_n6_ssd_mobilenet_v2_fpnlite_config.yaml
[WARNING] The usable GPU memory is unlimited.
Please consider setting the 'gpu_memory_limit' attribute in the 'general' section of your configuration file.
[INFO] : Running `deployment` operation mode
[INFO] : The random seed for this simulation is 123
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
[INFO] : Generating C header file for Getting Started...
[INFO] : This TFLITE model doesnt contain a post-processing layer
loading model.. model_path="../../stm32ai-modelzoo/object_detection/ssd_mobilenet_v2_fpnlite/ST_pretrainedmodel_public_dataset/coco_2017_person/ssd_mobilenet_v2_fpnlite_035_192/ssd_mobilenet_v2_fpnlite_035_192_int8.tflite"
loading conf file.. "../../application_code/object_detection/STM32N6/stmaic_STM32N6570-DK.conf" config="None"
"n6 release" configuration is used
[INFO] : Selected board : "STM32N6570-DK Getting Started Object Detection (STM32CubeIDE)" (stm32_cube_ide/n6 release/stm32n6)
[INFO] : Compiling the model and generating optimized C code + Lib/Inc files: ../../stm32ai-modelzoo/object_detection/ssd_mobilenet_v2_fpnlite/ST_pretrainedmodel_public_dataset/coco_2017_person/ssd_mobilenet_v2_fpnlite_035_192/ssd_mobilenet_v2_fpnlite_035_192_int8.tflite
setting STM.AI tools.. root_dir="", req_version=""
 Cube AI Path: "/opt/ST/STEdgeAICore/2.0/Utilities/linux/stedgeai".
[INFO] : Offline CubeAI used; Selected tools: 10.0.0 (x-cube-ai pack)
loading conf file.. "../../application_code/object_detection/STM32N6/stmaic_STM32N6570-DK.conf" config="None"
"n6 release" configuration is used
compiling... "ssd_mobilenet_v2_fpnlite_035_192_int8_tflite" session
 model_path : ['../../stm32ai-modelzoo/object_detection/ssd_mobilenet_v2_fpnlite/ST_pretrainedmodel_public_dataset/coco_2017_person/ssd_mobilenet_v2_fpnlite_035_192/ssd_mobilenet_v2_fpnlite_035_192_int8.tflite']
 tools : 10.0.0 (x-cube-ai pack)
 target : "STM32N6570-DK Getting Started Object Detection (STM32CubeIDE)" (stm32_cube_ide/n6 release/stm32n6)
 options : --st-neural-art default@../../application_code/object_detection/STM32N6/Model/user_neuralart.json --input-data-type uint8 --inputs-ch-position chlast
[returned code = 255 - FAILED]
Error executing job with overrides: []
Traceback (most recent call last):
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/stm32ai_main.py", line 207, in main
 process_mode(cfg)
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/stm32ai_main.py", line 99, in process_mode
 deploy(cfg)
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/../deployment/deploy.py", line 111, in deploy
 stm32ai_deploy_stm32n6(target=board, stlink_serial_number=stlink_serial_number, stm32ai_version=stm32ai_version, c_project_path=c_project_path,
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/../../common/deployment/common_deploy.py", line 515, in stm32ai_deploy_stm32n6
 stmaic_local_call(session)
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/../../common/deployment/common_deploy.py", line 489, in stmaic_local_call
 stmaic.compile(session=session, options=opt, target=session._board_config)
 File "/home/kartikkhandewal/stm32packages/stm32ai-modelzoo-services/object_detection/src/../../common/stm32ai_local/compile.py", line 214, in cmd_compile
 raise Exception('WRONG!')
Exception: WRONG!

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

 

 

I am using Ubuntu 22.04

[Julian E.]

Hello @athern27 ,

 

Can you attach your user_config.json?

Also, make sure to connect your N6 using a usb C to usb C cable on the stlink port. 

 

 

Try to put both button to the left and flash and then to the right (I don't remember which side it should be).

When changing the side, you need to unplug and plug again the N6

 

Have a good day,

Julian

[athern27]

Sorry for the late response. 
I didn't had a USB-C to C cable so I had to buy it. 
I tried running the program again but it still gave me the same error. I didn't find any user_config.json. But I did find deployment_n6_ssd_mobilenet_v2_fpnlite_config.yaml so I am attaching it as a txt file.

[Julian E.]

Hello @athern27 ,

 

Thank you for the yaml, I will try to reproduce on my side.

Have a good day,

Julian

[Julian E.]

Hello @athern27 ,

 

Your config is correct, I did not have an issue.

We think it maybe have something to do with root right on stedgeai. 

Can you try to use these commands:

chmod -R u+rwx /opt/ST/STEdgeAI/2.0
sudo chown -R $(whoami) /opt/ST/STEdgeAI/2.0

And retry to use the model zoo scripts.

 

Have a good day.

Julian

[athern27]

Hi @Julian E. ,

I didn't have access to my company PC's COM ports. After gaining access, I ran the commands, but they still didn’t work. Then, I decided to delete STEdgeAI and STM32CubeIDE and reinstall them in a different location. After reinstalling them, I was able to run the code.

Thank you for your support.

 

 

[Julian E.]

Hello @athern27 ,

 

Thank you for the update.
Good luck with your project

 

Have a good day,

Julian