Inference on external data #8
Description
Hi Dear Authors,
First and foremost, thank you very much for your excellent work on IPGN—it has been incredibly helpful for my research!
I have been trying to use your pre-trained IPGN model for inference. I successfully ran the inference script on the provided PTL dataset, which worked perfectly. However, when I attempted to perform inference on other pulmonary tree masks, the model’s performance degraded severely.
I was wondering if I might have missed some key preprocessing or setup steps. Currently, I only reoriented the data to be consistent with the PTL dataset. Could you kindly advise me on what additional steps I should take to improve the model’s performance on external pulmonary tree masks?
Thank you so much for your time and help in advance. I really appreciate your guidance!