Speeding up proccess

[zratclif]

Hello, me and a group of people are using Garfield for an object recognition research project. This includes us uploading custom data into Garfield and utilizing the software to manipulate scenes. When training this data with an ADA6000 Nvidia GPU we see load times of 45-90 minutes. Is there any way we can cut this time down, while not sacrificing our quality too much?

[chungmin99]

Hi! Sorry for the late reply -- does this dataset have a lot of images (500+)? GARField preprocessing time scales linearly w/ the # of training images (running SAM's automatic mask generator per-image). The quickest thing to try would be to decrease or subsample the number of images (especially if they're very similar / near-duplicates).