# Error in Nvidia AIAA

**URL:** <https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730>\
**Category:** Support\
**Created:** [November 22, 2021, 4:55pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730 "2021-11-22T16:55:02Z")\
**Posts on this page:** 17\
**Page:** 2

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [May 6, 2022, 12:49pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/22 "2022-05-06T12:49:08Z")

</div>

You can ask MONAILabel developers to help you port the old model into a MONAILabel app.

@diazandr3s

---

<div class="post-metadata">

**Author:** ![diazandr3s](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/diazandr3s/32/9973_2.png) [@diazandr3s](https://discourse.slicer.org/u/diazandr3s)\
**Post date:** [May 6, 2022, 2:02pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/23 "2022-05-06T14:02:27Z")

</div>

Thanks for the ping, @lassoan

@Pari_TF, have you considered using MONAI Label ([GitHub - Project-MONAI/MONAILabel: MONAI Label is an intelligent open source image labeling and learning tool.](https://github.com/Project-MONAI/MONAILabel))?

It is easy to get a pretrained model for lung segmentation using MONAI Label. Are you using a public dataset?

---

<div class="post-metadata">

**Author:** ![Pari\_TF](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/pari_tf/32/15222_2.png) [@Pari\_TF](https://discourse.slicer.org/u/Pari_TF)\
**Post date:** [May 12, 2022, 12:59pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/24 "2022-05-12T12:59:35Z")

</div>

Thanks for your reply. No, I haven’t used MONAI Label. That’s great. I will try it. Thank you so much. Yes, I’m working on a public dataset.

---

<div class="post-metadata">

**Author:** ![scorey1983](https://avatars.discourse-cdn.com/v4/letter/s/ba9def/32.png) [@scorey1983](https://discourse.slicer.org/u/scorey1983)\
**Post date:** [May 18, 2022, 9:10am UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/25 "2022-05-18T09:10:52Z")

</div>

I am using my own data to segment lung nodules. The training set has been using the annotation\_lung\_tumor model of Nvidia AIAA. Now that the test set is ready, I found that the above model is no longer available, which caused me a lot of trouble. Can you help me add the old model to MONAI Label, thanks.

---

<div class="post-metadata">

**Author:** ![diazandr3s](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/diazandr3s/32/9973_2.png) [@diazandr3s](https://discourse.slicer.org/u/diazandr3s)\
**Post date:** [May 18, 2022, 11:09pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/26 "2022-05-18T23:09:17Z")

</div>

Do you know which dataset they used to get that pretrained model? I think it is Task06\_Lung ([MSD - Google Drive](https://drive.google.com/drive/folders/1HqEgzS8BV2c7xYNrZdEAnrHk7osJJ--2)) from the Medical Segmentation Decathlon but I’m not sure.

If that’s the dataset, you should be able to get a pretrained model fairly easy. Do you have a GPU-based PC?

---

<div class="post-metadata">

**Author:** ![scorey1983](https://avatars.discourse-cdn.com/v4/letter/s/ba9def/32.png) [@scorey1983](https://discourse.slicer.org/u/scorey1983)\
**Post date:** [May 19, 2022, 2:55am UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/27 "2022-05-19T02:55:59Z")

</div>

It is indeed a model pre-trained with the Task06\_Lung dataset, and we use boundary-point based segmentation of lung tumor on CT (AIAA for 3D Slicer). But now the model is not found in NVIDIA. Also, we have GPU-based PC.

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [May 19, 2022, 11:15am UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/28 "2022-05-19T11:15:50Z")

</div>

> [@diazandr3s](#):
>
> It is easy to get a pretrained model for lung segmentation using MONAI Label. Are you using a public dataset?

I was going to try this out but I am consistently running into

```auto
monailabel apps --download --name deepedit --output apps
Using PYTHONPATH=/home/rbumm:
App deepedit => /usr/monailabel/sample-apps/deepedit not exists

```

after a

```auto
pip install monailabel

```

This is with and w/o an elevated bash on Windows 10 Ubuntu WSL. Any ideas?

---

<div class="post-metadata">

**Author:** ![diazandr3s](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/diazandr3s/32/9973_2.png) [@diazandr3s](https://discourse.slicer.org/u/diazandr3s)\
**Post date:** [May 19, 2022, 12:30pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/29 "2022-05-19T12:30:19Z")

</div>

@rbumm there were recently some changes in folder structure. Please try out the monailabel-weekly instead (pip install monailabel-weekly)

Then download the radiology app as follows:

```
monailabel apps --download --name radiology --output apps

```

As an example you could download and use the spleen dataset:

```
monailabel datasets --download --name Task09_Spleen --output datasets

```

Then start the server using the Deepedit model:

```
monailabel start_server --app apps/radiology --studies datasets/Task09_Spleen/imagesTr --conf models deepedit

```

Here you can see more details: [GitHub - Project-MONAI/MONAILabel: MONAI Label is an intelligent open source image labeling and learning tool.](https://github.com/Project-MONAI/MONAILabel#release-candidate)

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [May 19, 2022, 12:48pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/30 "2022-05-19T12:48:14Z")

</div>

> [@diazandr3s](#):
>
> pip install monailabel-weekly

Thanks, Andres, tried this already - pip uninstalled monailabel and pip installed monailabel-weekly, but there is a similar message:

```auto
monailabel apps --download --name radiology --output apps
Using PYTHONPATH=/home/rbumm:
App radiology => /usr/monailabel/sample-apps/radiology not exists

```

Probably a permission problem.

---

<div class="post-metadata">

**Author:** ![diazandr3s](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/diazandr3s/32/9973_2.png) [@diazandr3s](https://discourse.slicer.org/u/diazandr3s)\
**Post date:** [May 19, 2022, 6:06pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/32 "2022-05-19T18:06:17Z")

</div>

This is strange 😕  
Probably the weekly installation wasn’t clean. Please do a clean installation using a clean Python virtual environment.

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [May 20, 2022, 12:40pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/33 "2022-05-20T12:40:39Z")

</div>

Needed to install monailabel via github to make this working in Windows 10 WSL ([see here](https://discourse.slicer.org/t/how-to-start-with-monailabel-for-new-models/21063/31)).

---

<div class="post-metadata">

**Author:** ![diazandr3s](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/diazandr3s/32/9973_2.png) [@diazandr3s](https://discourse.slicer.org/u/diazandr3s)\
**Post date:** [May 20, 2022, 4:04pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/34 "2022-05-20T16:04:43Z")

</div>

Hi @rbumm,

My bad, I just realised the weekly version doesn’t install the candidate release 0.4.0 🙁  
In order to use the radiology app you should either use directly the GitHub repo as you did or install directly the candidate release:

pip install monailabel==0.4.0rc3

Please let me know how that goes. Happy to help.

Andres

---

<div class="post-metadata">

**Author:** ![Bor\_Antolic](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/bor_antolic/32/17628_2.png) [@Bor\_Antolic](https://discourse.slicer.org/u/Bor_Antolic)\
**Post date:** [January 3, 2023, 1:55pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/35 "2023-01-03T13:55:00Z")

</div>

Hi!  
I would like to use NVidia AIAA in 3d Slicer on my work (hospital) computer.  
I get the error  
Failed to fetch models from remote server. Make sure server address is correct and \<server\_uri\>/v1/models is accessible in browser

I cannot access [http://perklabseg.asuscomm.com:5000/v1/models](http://perklabseg.asuscomm.com:5000/v1/models) from my browser.  
I am probably behind a proxy. How I can configure the settings, so the AIAA would work?  
Thanks!  
Bor

---

<div class="post-metadata">

**Author:** ![xux7306](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/xux7306/32/77313_2.png) [@xux7306](https://discourse.slicer.org/u/xux7306)\
**Post date:** [July 14, 2024, 4:07am UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/36 "2024-07-14T04:07:48Z")

</div>

Hello, I entered the URL `http://perklabseg.asuscomm.com:5000/v1/models`, but it shows that `perklabseg.asuscomm.com` is currently unable to handle this request. HTTP ERROR 502. What should I do? I can’t connect to the default server. Please help me.

---

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [July 14, 2024, 2:07pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/37 "2024-07-14T14:07:58Z")

</div>

This is a quickly evolving field. We don’t provide the NVIDIA AIAA demo server anymore, as the developers of this segmentation tool moved on to new technologies.

You can now use tools such as [MONAIAuto3DSeg](https://github.com/lassoan/SlicerMONAIAuto3DSeg) and [TotalSegmentator](https://github.com/lassoan/SlicerTotalSegmentator?tab=readme-ov-file#totalsegmentator) extensions for simple server-less running of pre-trained models and [MONAILabel](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/slicer#readme) for training your own models.

---

<div class="post-metadata">

**Author:** ![jamesobutler](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/jamesobutler/32/7511_2.png) [@jamesobutler](https://discourse.slicer.org/u/jamesobutler)\
**Post date:** [July 14, 2024, 5:50pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/38 "2024-07-14T17:50:58Z")

</div>

@lassoan Is it time to archive Nvidia AIAA from the Slicer extensions index? Otherwise it is likely a “tier 5” extension as it is not under active development with little to no support. This will help the community better understand what are the higher quality AI based extensions to use in Slicer.

> <https://github.com/Slicer/ExtensionsIndex/blob/de1784752880fbb490262060da28efb81aa96893/NvidiaAIAssistedAnnotation.json>

---

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [July 14, 2024, 6:47pm UTC](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730/39 "2024-07-14T18:47:19Z")

</div>

I agree, making it a low-tier extension (when the tier system is introduced) is a good idea.

[Previous page](https://discourse.slicer.org/t/error-in-nvidia-aiaa/20730.md?page=1)
