# MonaiLabel on 8GB GPU

**URL:** <https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239>\
**Category:** Support\
**Tags:** monailabel\
**Created:** [January 14, 2023, 4:28pm UTC](https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239 "2023-01-14T16:28:06Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![mau\_igna\_06](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/mau_igna_06/32/9056_2.png) [@mau\_igna\_06](https://discourse.slicer.org/u/mau_igna_06)\
**Post date:** [January 14, 2023, 4:28pm UTC](https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239/1 "2023-01-14T16:28:06Z")

</div>

Hi

I was trying the vertebrae segmentation pipeline sample-app and I runned out of memory on a small CT

Does it make sense to spend time trying to reconfigure it to get it working? Will the quality of the modified algorithm be too low?

Could you give pointers/recommendations on cloud options?

Thanks a lot

---

<div class="post-metadata">

**Author:** ![pieper](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/pieper/32/8_2.png) [@pieper](https://discourse.slicer.org/u/pieper)\
**Post date:** [January 14, 2023, 4:36pm UTC](https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239/2 "2023-01-14T16:36:52Z")

</div>

I was having a similar problem running out of GPU memory. I created a new conda environment and explicitly installed the CPU version of pytorch (using their install wizard: [Start Locally | PyTorch](https://pytorch.org/get-started/locally/)). Running monailabel server in this environment bypassed the GPU. Inference runs multithreaded is still pretty quick.

---

<div class="post-metadata">

**Author:** ![mau\_igna\_06](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/mau_igna_06/32/9056_2.png) [@mau\_igna\_06](https://discourse.slicer.org/u/mau_igna_06)\
**Post date:** [January 14, 2023, 5:33pm UTC](https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239/3 "2023-01-14T17:33:07Z")

</div>

I was trying to keep it very simple by using the Docker monai-label server because I just want to test one CT currently.  
I guess I’ll have to take more time than I initially planned to deploy anaconda, pytorch and monai-label

---

<div class="post-metadata">

**Author:** ![pieper](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/pieper/32/8_2.png) [@pieper](https://discourse.slicer.org/u/pieper)\
**Post date:** [January 14, 2023, 5:48pm UTC](https://discourse.slicer.org/t/monailabel-on-8gb-gpu/27239/4 "2023-01-14T17:48:48Z")

</div>

It’s really pretty straightforward to install miniconda and then install torch and monai label. It really shouldn’t take more than a few minutes. Let us know how it goes.