About random sampling in eval_7andN

[zechengtang]

Hi @mystorm16 , thanks for your impressive and practical work! When I read your code, I have some question about the following code in eval_7andN.py:

                # If number of points exceeds threshold, sample by points
                if pts_all_masked.shape[0] > 999999:
                    sample_indices = np.random.choice(
                        pts_all_masked.shape[0], 999999, replace=False
                    )
                    pts_all_masked = pts_all_masked[sample_indices]
                    images_all_masked = images_all_masked[sample_indices]


                # Apply the same sampling to GT point cloud
                if pts_gt_all_masked.shape[0] > 999999:
                    sample_indices_gt = np.random.choice(
                        pts_gt_all_masked.shape[0], 999999, replace=False
                    )
                    pts_gt_all_masked = pts_gt_
                    all_masked[sample_indices_gt]

Why do you do a random sampling here which uses different indices to select pts_gt_all_masked and pts_all_masked?