loading cameras occupies too much ram？

[Livioni]

I got stuck at this step when I first loaded the Rubble dataset, which took up 100+G of RAM. I'm wondering if I did the right thing.

I set resolution = 4

https://github.com/kangpeilun/VastGaussian/blob/2d03641643fcc23e78557d543b1fa9b09e901e0a/scene/datasets.py#L82C1-L88C81

        for resolution_scale in resolution_scales:
            print("Loading Training Cameras")
            self.train_cameras[resolution_scale] = cameraList_from_camInfos(scene_info.train_cameras, resolution_scale,
                                                                            args)
            print("Loading Test Cameras")
            self.test_cameras[resolution_scale] = cameraList_from_camInfos(scene_info.test_cameras, resolution_scale,
                                                                           args)

[ZhangZhan-YC]

There are too many cameras in the MILL_19 datasets,(1940 imgaes).So i think partition should be done befor the cameraList_from_camInfos().

[Livioni]

There are too many cameras in the MILL_19 datasets,(1940 imgaes).So i think partition should be done befor the cameraList_from_camInfos().

I'm trying to load the minimum data to do the split and see if it works on my 128G RAM server.

[Livioni]

I added a separate script to perform the partitioning operation that only needs to load the point cloud data and camera data. #10