update torch.div and torch.meshgrid to remove warning

pcdet/models/model_utils/centernet_utils.py

@@ -139,11 +139,11 @@ def _topk(scores, K=40):
     topk_scores, topk_inds = torch.topk(scores.flatten(2, 3), K)
 
     topk_inds = topk_inds % (height * width)
-    topk_ys = (topk_inds // width).float()
+    topk_ys = torch.div(topk_inds, width, rounding_mode='floor').float()
     topk_xs = (topk_inds % width).int().float()
 
     topk_score, topk_ind = torch.topk(topk_scores.view(batch, -1), K)
-    topk_classes = (topk_ind // K).int()
+    topk_classes = torch.div(topk_ind, K, rounding_mode='floor').int()
     topk_inds = _gather_feat(topk_inds.view(batch, -1, 1), topk_ind).view(batch, K)
     topk_ys = _gather_feat(topk_ys.view(batch, -1, 1), topk_ind).view(batch, K)
     topk_xs = _gather_feat(topk_xs.view(batch, -1, 1), topk_ind).view(batch, K)

pcdet/ops/pointnet2/pointnet2_stack/pointnet2_modules.py

@@ -349,7 +349,7 @@ class VectorPoolAggregationModule(nn.Module):
         x_grids = torch.arange(-R + R / num_voxels[0], R - R / num_voxels[0] + 1e-5, 2 * R / num_voxels[0], device=device)
         y_grids = torch.arange(-R + R / num_voxels[1], R - R / num_voxels[1] + 1e-5, 2 * R / num_voxels[1], device=device)
         z_grids = torch.arange(-R + R / num_voxels[2], R - R / num_voxels[2] + 1e-5, 2 * R / num_voxels[2], device=device)
-        x_offset, y_offset, z_offset = torch.meshgrid(x_grids, y_grids, z_grids)  # shape: [num_x, num_y, num_z]
+        x_offset, y_offset, z_offset = torch.meshgrid(x_grids, y_grids, z_grids, indexing='ij')  # shape: [num_x, num_y, num_z]
         xyz_offset = torch.cat((
             x_offset.contiguous().view(-1, 1),
             y_offset.contiguous().view(-1, 1),