thyroid_segmentation
thyroid_segmentation copied to clipboard
How to train at jpg images instead of dicom data?
Hi, thank you for reading my issue!
I have a dataset consisting of about 1k thyroid ultrasound images(1k jpg images+ 1k png groundtruth masks). After I had read some codes of this repository, I found I don't know how to train at a single image instead of the .dcm data.
Can you teach me how to modify the code to meet my needs?