search

microsoft / InnerEye-DeepLearning

Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning
https://aka.ms/innereyeoss
MIT License
557 stars 142 forks source link

Possibility to run without Azure #242

Closed sycured closed 4 years ago

sycured commented 4 years ago

It'll be interesting for development purpose to be able to run it entirely on localhost without needing Azure.

In addition, a company without the right to use (specific or any) cloud provider can later be authorized and during this time can use InnerEye

ant0nsc commented 4 years ago

The code runs perfectly fine without Azure. We are using runs on local dev boxes for model development and debugging. But of course, to build any reasonably large model, you would need a machine that has a GPU. Project InnerEye is also working with the Azure Stack Hub team, which helps healthcare providers and ISVs to provide low latency medical image analysis, while complying with local handling regulations - it pretty much gives you cloud capabilities on-premise. If that's of interest to you, please contact InnerEyeCommercial@microsoft.com to discuss.

ant0nsc commented 4 years ago

I added a sentence to README in #243 that I hope clarifies this. I'll close this issue when the PR goes in - please re-open if you feel there are still questions.