Open gnool opened 5 years ago
Do you mean 2-3k pixel per side? This will increase training time and you will need a whole lot of (v)ram for this. Do you really need to have such a high resolution? Could you not either downscale+upscale (+grabcut if needed or so) or cut images and then feed them in?
greetings to all experts here, i have been using deeplab for some time now, but am always limited by the low resolution image input. My images are always of rather high resolution (2k-3k). Does anyone know if there is a higher resolution version of deeplab? If not, is it even feasible to create one that supports much higher resolution (as well as train it), i.e. is the training time going to be exponentially longer?