dynamic_voxelnet.py

# Copyright (c) OpenMMLab. All rights reserved.
from typing import List, Tuple

import torch
from mmcv.runner import force_fp32
from torch import Tensor
from torch.nn import functional as F

from mmdet3d.registry import MODELS
from mmdet3d.utils import ConfigType, OptConfigType, OptMultiConfig
from .voxelnet import VoxelNet


@MODELS.register_module()
class DynamicVoxelNet(VoxelNet):
    r"""VoxelNet using `dynamic voxelization <https://arxiv.org/abs/1910.06528>`_.
    """

    def __init__(self,
                 voxel_layer: ConfigType,
                 voxel_encoder: ConfigType,
                 middle_encoder: ConfigType,
                 backbone: ConfigType,
                 neck: OptConfigType = None,
                 bbox_head: OptConfigType = None,
                 train_cfg: OptConfigType = None,
                 test_cfg: OptConfigType = None,
                 data_preprocessor: OptConfigType = None,
                 init_cfg: OptMultiConfig = None) -> None:
        super().__init__(
            voxel_layer=voxel_layer,
            voxel_encoder=voxel_encoder,
            middle_encoder=middle_encoder,
            backbone=backbone,
            neck=neck,
            bbox_head=bbox_head,
            train_cfg=train_cfg,
            test_cfg=test_cfg,
            data_preprocessor=data_preprocessor,
            init_cfg=init_cfg)

    @torch.no_grad()
    @force_fp32()
    def voxelize(self, points: List[torch.Tensor]) -> tuple:
        """Apply dynamic voxelization to points.

        Args:
            points (list[Tensor]): Points of each sample.

        Returns:
            tuple[Tensor]: Concatenated points and coordinates.
        """
        coors = []
        # dynamic voxelization only provide a coors mapping
        for res in points:
            res_coors = self.voxel_layer(res)
            coors.append(res_coors)
        points = torch.cat(points, dim=0)
        coors_batch = []
        for i, coor in enumerate(coors):
            coor_pad = F.pad(coor, (1, 0), mode='constant', value=i)
            coors_batch.append(coor_pad)
        coors_batch = torch.cat(coors_batch, dim=0)
        return points, coors_batch

    def extract_feat(self, batch_inputs_dict: dict) -> Tuple[Tensor]:
        """Extract features from points."""
        # TODO: Remove voxelization to datapreprocessor
        points = batch_inputs_dict['points']
        voxels, coors = self.voxelize(points)
        voxel_features, feature_coors = self.voxel_encoder(voxels, coors)
        batch_size = coors[-1, 0].item() + 1
        x = self.middle_encoder(voxel_features, feature_coors, batch_size)
        x = self.backbone(x)
        if self.with_neck:
            x = self.neck(x)
        return x