Fail to open AddaxAI

Hi there!

I’m a new user of the AddaxAI, I want to ask a question that may be simple and kind of silly, but I can’t open the AddaxAI after a successful installtion under windos 10 system. I have got a shortcut file on my desktop, I double clicked it but nothing happened. I also tried to start it as administrator, but it still did’t work.
Just in case, my PC has a NVIDIA Quadro P400 GPU.

Thanks!

Hi @Mingzhang_Liu ,

Would you be able to share the logs after opening it in debug mode?

That will give me some more information as to whats going on.

Thanks!

Cheers,

Peter

Hi peter! Thanks for your reply. Here is what I got in debug mode, is it about the python environment…? I only got python attached to arcgis on my PC.

Hi @Mingzhang_Liu ,

That seems to be a corrupted file issue. Can you try reinstalling AddaxAI all together and see if that works?

Cheers,

Peter

Hi @petervanlunteren , I uninstall the software as suggested by deleting the AddaxAI_files folder. Then I install it again, which should be successful as shown below, then I double clicked the shortcut file and again nothing happened. I ran the debug mode and the result was exactly the same as last time.

Thanks for checking @Mingzhang_Liu!

Could you open C:\Users\<username>\AddaxAI_files\AddaxAI\model_info\model_info_v5.json in a text editor like VS Code or Notepad++ and check:

  • Is it readable text?
  • Does it contain weird symbols?
  • Is it actually valid JSON?

Hi @petervanlunteren , I open the model info files with notepad and they generally look like below. So I think they are readable, I do not see wired symbols, but I’m don’t know how to check whether they are valid JASON.

Great, that tells me a lot! I just did a code change on how the device should interpret the file. The default on your device is probabaly set to some other encoding.

It’s already build and ready. Can you try to reinstall it again? Please use the latest intaller from the website.

Does that work for you?

It works now! Thank you very much for your help @petervanlunteren !!!

Cheers,
Mingzhang Liu

1 Like

Hi @petervanlunteren , I met another problem here, please see the error report and all traceback below.Processing: 微信图片_20260204101140_211_5.png…
Again thank you very much for your time!
SpeciesNet is starting up…

C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\yolov5\utils\general.py:34: UserWarning: pkg_resources is deprecated as an API. See Package Discovery and Resource Access using pkg_resources - setuptools 80.10.2 documentation. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.

import pkg_resources as pkg

I0204 10:12:04.056918 8844 classifier.py:109] Loaded SpeciesNetClassifier in 2.64 seconds on CPU.

Traceback (most recent call last):

File “”, line 198, in _run_module_as_main

File “”, line 88, in _run_code

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\speciesnet\scripts\run_model.py”, line 476, in

app.run(main)

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\absl\app.py”, line 367, in run

_run_main(main, args)

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\absl\app.py”, line 312, in _run_main

sys.exit(main(argv))

         ^^^^^^^^^^

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\speciesnet\scripts\run_model.py”, line 398, in main

model = SpeciesNet(

        ^^^^^^^^^^^

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\speciesnet\multiprocessing.py”, line 610, in init

self.detector = SpeciesNetDetector(model_name)

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\speciesnet\detector.py”, line 81, in init

checkpoint = torch.load(

             ^^^^^^^^^^^

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\torch\serialization.py”, line 1486, in load

with _open_zipfile_reader(opened_file) as opened_zipfile:

     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File “C:\Users\dell\AddaxAI_files\envs\env-speciesnet\Lib\site-packages\torch\serialization.py”, line 771, in init

super().__init__(torch._C.PyTorchFileReader(name_or_buffer))

                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

Converting SpeciesNet output to AddaxAI format…
Traceback (most recent call last):

File “C:\Users\dell\AddaxAI_files\AddaxAI\classification_utils\model_types\speciesnet_to_md.py”, line 339, in

main()

File “C:\Users\dell\AddaxAI_files\AddaxAI\classification_utils\model_types\speciesnet_to_md.py”, line 333, in main

generate_md_results_from_predictions_json(

File “C:\Users\dell\AddaxAI_files\AddaxAI\classification_utils\model_types\speciesnet_to_md.py”, line 102, in generate_md_results_from_predictions_json

with open(predictions_json_file, "r") as f:

     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

FileNotFoundError: [Errno 2] No such file or directory: ‘E:\Liu Mingzhang\N10E1\sppnet_output_file.json’

Converting Done!

Adding AddaxAI metadata…

Hi @Mingzhang_Liu

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

It’s a corrupted checkpoint file, which often means the weights download was interrupted, or got blocked by security issues.

Are you by any chance on a highly secure network, like a university, government? Or are you on an unstable ineternet connection?

Could you try downloading the weights file again?

Please do so by removing this folder with all its contents: C:\Users\<username>\AddaxAI_files\models\cls\Global - SpeciesNet - Google, and restarting AddaxAI.

You can now choose to download the model again.

Does that work? Please make sure you have good and stable internet connection. If the error persists, could you try switching to a different network? Perhaps your home wifi where the security might be less limiting?

Cheers,

Peter