SAMed
SAMed copied to clipboard
Question for Code and Dataset
Thank you for your contribution :)
Q1. Trainer.py 94 lines, assert image_batch.max() <= 3 Is this aim to color channel restriction?
Q2. How do I normalize my dataset to train? I think, Image is often normalized by 0~1 or 0~255 but your dataset is not I see that your dataset range is -1 to 2(maybe..)
Thank you.
Q1: This is a legacy for debug. It just restricts the data range. Q2: We have released the entire preprocess scripts in the preprocess directory.