Pointnet++代码详解（七）：PointNetSetAbstractionMsg层

捕获多尺度模式的方法是应用不同尺度的分组层，然后根据点来提取每个尺度的特征。将不同尺度的特征串联起来，形成多尺度特征。使用 Multi-Scale Grouping（MSG）方法的SA层：

大部分的形式都与普通的SA层相似，但是这里radius_list输入的是一个list例如[0.1,0.2,0.4]，对于不同的半径做ball query，最终将不同半径下的点点云特征保存在new_points_list中，再最后拼接到一起。具体代码如下：

class PointNetSetAbstractionMsg(nn.Module):
    def __init__(self, npoint, radius_list, nsample_list, in_channel, mlp_list):
        super(PointNetSetAbstractionMsg, self).__init__()
        ''' 
        PointNet Set Abstraction (SA) module with Multi-Scale Grouping (MSG)
        Input:
            xyz: (batch_size, ndataset, 3) TF tensor
            points: (batch_size, ndataset, channel) TF tensor
            npoint: int32 -- #points sampled in farthest point sampling
            radius_list: list of float32 -- search radius in local region
            nsample_list: list of int32 -- how many points in each local region
            mlp_list: list of list of int32 -- output size for MLP on each point
        Return:
            new_xyz: (batch_size, npoint, 3) TF tensor
            new_points: (batch_size, npoint, sum_k{mlp[k][-1]}) TF tensor
    '''
        self.npoint = npoint
        self.radius_list = radius_list
        self.nsample_list = nsample_list
        self.conv_blocks = nn.ModuleList()
        self.bn_blocks = nn.ModuleList()
        for i in range(len(mlp_list)):
            convs = nn.ModuleList()
            bns = nn.ModuleList()
            last_channel = in_channel + 3
            for out_channel in mlp_list[i]:
                convs.append(nn.Conv2d(last_channel, out_channel, 1))
                bns.append(nn.BatchNorm2d(out_channel))
                last_channel = out_channel
            self.conv_blocks.append(convs)
            self.bn_blocks.append(bns)

    def forward(self, xyz, points):
        """
        Input:
            xyz: input points position data, [B, C, N]
            points: input points data, [B, D, N]
        Return:
            new_xyz: sampled points position data, [B, C, S]
            new_points_concat: sample points feature data, [B, D', S]
        """
        xyz = xyz.permute(0, 2, 1)
        if points is not None:
            points = points.permute(0, 2, 1)

        B, N, C = xyz.shape
        S = self.npoint
        new_xyz = index_points(xyz, farthest_point_sample(xyz, S))
        new_points_list = []
        for i, radius in enumerate(self.radius_list):
            K = self.nsample_list[i]
            group_idx = query_ball_point(radius, K, xyz, new_xyz)
            grouped_xyz = index_points(xyz, group_idx)
            grouped_xyz -= new_xyz.view(B, S, 1, C)
            if points is not None:
                grouped_points = index_points(points, group_idx)
                grouped_points = torch.cat([grouped_points, grouped_xyz], dim=-1)
            else:
                grouped_points = grouped_xyz

            grouped_points = grouped_points.permute(0, 3, 2, 1)  # [B, D, K, S]
            for j in range(len(self.conv_blocks[i])):
                conv = self.conv_blocks[i][j]
                bn = self.bn_blocks[i][j]
                grouped_points =  F.relu(bn(conv(grouped_points)))
            new_points = torch.max(grouped_points, 2)[0]  # [B, D', S]
            new_points_list.append(new_points)

        new_xyz = new_xyz.permute(0, 2, 1)
        new_points_concat = torch.cat(new_points_list, dim=1)
        return new_xyz, new_points_concat