Hello. I have been looking for a way to train this model with my own segmentation data, but I only find the way to train several predefined datasets. Do I have to convert my dataset to the style of one of those available in order to train? Or is there an easier way? My dataset is composed of input images and output binary images for each channel.
Hello. I have been looking for a way to train this model with my own segmentation data, but I only find the way to train several predefined datasets. Do I have to convert my dataset to the style of one of those available in order to train? Or is there an easier way? My dataset is composed of input images and output binary images for each channel.
Thanks