matteformer
matteformer copied to clipboard
Inference size
Does the image needs to be 512x512? Or can we input higher res images?
Hi, we use 512x512 images when training the model. But you can put any size of image you want (as long as your gpu memory allows)
@AeroDEmi on a GPU with 24GB of memory, I was able to get up to around 2900x2900 pixels.
@AeroDEmi on a GPU with 24GB of memory, I was able to get up to around 2900x2900 pixels.
How does it work under the hood? Does is resize input image or there is tile processing implemented?