Hi @ceceshao1 - thanks for your comments. I will take a look at comet.ml though have gone down the path of doing things myself for now - will see how I get on (it’s more for my learning as much as anything).
Re. TTA it’s because the fast.ai version I was using didn’t support it for image segmentation per here. Note for a classification problem it’s fine as a label of cat is still a cat when you (for example) rotate it but for pixel level predictions you need to know the transform and be able to sensibly reverse it. As such people only did lr flips as far as I know (but you couldn’t determine in fast.ai in the TTA preds which images were flipped). Things might have changed now in fast.ai v1.