Re-train the model with new data: 3 view aggregation

ai-med / quickNAT_pytorch

PyTorch Implementation of QuickNAT and Bayesian QuickNAT, a fast brain MRI segmentation framework with segmentation Quality control using structure-wise uncertainty

MIT License

101 stars 36 forks source link

Re-train the model with new data: 3 view aggregation #13

Closed rockNroll87q closed 4 years ago

rockNroll87q commented 5 years ago

Dear authors,

First of all, great work and thanks for the code! I'm trying to re-train the model with my data and it seems to run.

I only have a question. It seems possible to select the orientation (COR, AXI, SAG), but how I create a model that aggregate all of these 3?

Thanks!

abhi4ssj commented 4 years ago

Hi,

Details for training and deploying with View Aggregation is added in the recent commits. I omitted the SAG axis and only used AXI and COR for now to optimize between performance and deployment time.

Best Abhijit