1. 网络主体架构

以voxel_rcnn_car.yaml为例。

主要包括：

1. VFE(体素编码网络)，这里采用下MeanVFE;
2. BACKBONE_3D，这里采用VoxelBackBone8x;
3. MAP_TO_BEV，这里采用HeightCompression，NUM_BEV_FEATURES为256；
4. BACKBONE_2D，这里采用BaseBEVBackbone；
5. DENSE_HEAD，这里采用AnchorHeadSingle;
6. ROI_HEAD，这里采用VoxelRCNNHead;

2. VFE 模块

这里采用的MeanVFE, 这里的depth_downsample_factor 为None，因为在cfgs/dataset_configs/kitti_dataset.yaml中没有定义。
MeanVFE的实现：

这里

3. BACKBONE_3D 模块

这里采用VoxelBackBone8x

class VoxelBackBone8x(nn.Module):
    def __init__(self, model_cfg, input_channels, grid_size, **kwargs):
        super().__init__()
        self.model_cfg = model_cfg
        norm_fn = partial(nn.BatchNorm1d, eps=1e-3, momentum=0.01)

        self.sparse_shape = grid_size[::-1] + [1, 0, 0] # grid_size (1408,1600,40) input_channels : 4

        self.conv_input = spconv.SparseSequential(
            spconv.SubMConv3d(input_channels, 16, 3, padding=1, bias=False, indice_key='subm1'),
            norm_fn(16),
            nn.ReLU(),
        ) # 定义了一个稀疏卷积
        block = post_act_block

        self.conv1 = spconv.SparseSequential(
            block(16, 16, 3, norm_fn=norm_fn, padding=1, indice_key='subm1'),
        )

        self.conv2 = spconv.SparseSequential(
            # [1600, 1408, 41] <- [800, 704, 21]
            block(16, 32, 3, norm_fn=norm_fn, stride=2, padding=1, indice_key='spconv2', conv_type='spconv'),
            block(32, 32, 3, norm_fn=norm_fn, padding=1, indice_key='subm2'),
            block(32, 32, 3, norm_fn=norm_fn, padding=1, indice_key='subm2'),
        )

        self.conv3 = spconv.SparseSequential(
            # [800, 704, 21] <- [400, 352, 11]
            block(32, 64, 3, norm_fn=norm_fn, stride=2, padding=1, indice_key='spconv3', conv_type='spconv'),
            block(64, 64, 3, norm_fn=norm_fn, padding=1, indice_key='subm3'),
            block(64, 64, 3, norm_fn=norm_fn, padding=1, indice_key='subm3'),
        )

        self.conv4 = spconv.SparseSequential(
            # [400, 352, 11] <- [200, 176, 5]
            block(64, 64, 3, norm_fn=norm_fn, stride=2, padding=(0, 1, 1), indice_key='spconv4', conv_type='spconv'),
            block(64, 64, 3, norm_fn=norm_fn, padding=1, indice_key='subm4'),
            block(64, 64, 3, norm_fn=norm_fn, padding=1, indice_key='subm4'),
        )

        last_pad = 0
        last_pad = self.model_cfg.get('last_pad', last_pad)
        self.conv_out = spconv.SparseSequential(
            # [200, 150, 5] -> [200, 150, 2]
            spconv.SparseConv3d(64, 128, (3, 1, 1), stride=(2, 1, 1), padding=last_pad,
                                bias=False, indice_key='spconv_down2'),
            norm_fn(128),
            nn.ReLU(),
        )
        self.num_point_features = 128
        self.backbone_channels = {
            'x_conv1': 16,
            'x_conv2': 32,
            'x_conv3': 64,
            'x_conv4': 64
        }



    def forward(self, batch_dict):
        """
        Args:
            batch_dict:
                batch_size: int
                vfe_features: (num_voxels, C)
                voxel_coords: (num_voxels, 4), [batch_idx, z_idx, y_idx, x_idx]
        Returns:
            batch_dict:
                encoded_spconv_tensor: sparse tensor
        """
        voxel_features, voxel_coords = batch_dict['voxel_features'], batch_dict['voxel_coords']
        batch_size = batch_dict['batch_size']
        input_sp_tensor = spconv.SparseConvTensor(
            features=voxel_features,
            indices=voxel_coords.int(),
            spatial_shape=self.sparse_shape,
            batch_size=batch_size
        )

        x = self.conv_input(input_sp_tensor)

        x_conv1 = self.conv1(x)
        x_conv2 = self.conv2(x_conv1)
        x_conv3 = self.conv3(x_conv2)
        x_conv4 = self.conv4(x_conv3)

        # for detection head
        # [200, 176, 5] -> [200, 176, 2]
        out = self.conv_out(x_conv4)

        batch_dict.update({
            'encoded_spconv_tensor': out,
            'encoded_spconv_tensor_stride': 8
        })
        batch_dict.update({
            'multi_scale_3d_features': {
                'x_conv1': x_conv1,
                'x_conv2': x_conv2,
                'x_conv3': x_conv3,
                'x_conv4': x_conv4,
            }
        })
        batch_dict.update({
            'multi_scale_3d_strides': {
                'x_conv1': 1,
                'x_conv2': 2,
                'x_conv3': 4,
                'x_conv4': 8,
            }
        })

        return batch_dict

关于3d稀疏卷积的理解，可以看https://zhuanlan.zhihu.com/p/382365889