Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
voxelnet.py 4.68 KB
Newer Older
zhangwenwei's avatar
Initial commit  
zhangwenwei committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140 
import torch
import torch.nn.functional as F

from mmdet3d.ops import Voxelization
from mmdet.models.registry import DETECTORS
from .. import builder
from .single_stage import SingleStageDetector


@DETECTORS.register_module
class VoxelNet(SingleStageDetector):

    def __init__(self,
                 voxel_layer,
                 voxel_encoder,
                 middle_encoder,
                 backbone,
                 neck=None,
                 bbox_head=None,
                 train_cfg=None,
                 test_cfg=None,
                 pretrained=None):
        super(VoxelNet, self).__init__(
            backbone=backbone,
            neck=neck,
            bbox_head=bbox_head,
            train_cfg=train_cfg,
            test_cfg=test_cfg,
            pretrained=pretrained,
        )
        self.voxel_layer = Voxelization(**voxel_layer)
        self.voxel_encoder = builder.build_voxel_encoder(voxel_encoder)
        self.middle_encoder = builder.build_middle_encoder(middle_encoder)

    def extract_feat(self, points, img_meta):
        voxels, num_points, coors = self.voxelize(points)
        voxel_features = self.voxel_encoder(voxels, num_points, coors)
        batch_size = coors[-1, 0].item() + 1
        x = self.middle_encoder(voxel_features, coors, batch_size)
        x = self.backbone(x)
        if self.with_neck:
            x = self.neck(x)
        return x

    @torch.no_grad()
    def voxelize(self, points):
        voxels, coors, num_points = [], [], []
        for res in points:
            res_voxels, res_coors, res_num_points = self.voxel_layer(res)
            voxels.append(res_voxels)
            coors.append(res_coors)
            num_points.append(res_num_points)
        voxels = torch.cat(voxels, dim=0)
        num_points = torch.cat(num_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 voxels, num_points, coors_batch

    def forward_train(self,
                      points,
                      img_meta,
                      gt_bboxes_3d,
                      gt_labels_3d,
                      gt_bboxes_ignore=None):
        x = self.extract_feat(points, img_meta)
        outs = self.bbox_head(x)
        loss_inputs = outs + (gt_bboxes_3d, gt_labels_3d, img_meta)
        losses = self.bbox_head.loss(
            *loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
        return losses

    def forward_test(self, **kwargs):
        return self.simple_test(**kwargs)

    def forward(self, return_loss=True, **kwargs):
        if return_loss:
            return self.forward_train(**kwargs)
        else:
            return self.forward_test(**kwargs)

    def simple_test(self, points, img_meta, gt_bboxes_3d=None, rescale=False):
        x = self.extract_feat(points, img_meta)
        outs = self.bbox_head(x)
        bbox_inputs = outs + (img_meta, rescale)
        bbox_list = self.bbox_head.get_bboxes(*bbox_inputs)
        return bbox_list


@DETECTORS.register_module
class DynamicVoxelNet(VoxelNet):

    def __init__(self,
                 voxel_layer,
                 voxel_encoder,
                 middle_encoder,
                 backbone,
                 neck=None,
                 bbox_head=None,
                 train_cfg=None,
                 test_cfg=None,
                 pretrained=None):
        super(DynamicVoxelNet, self).__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,
            pretrained=pretrained,
        )

    def extract_feat(self, points, img_meta):
        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

    @torch.no_grad()
    def voxelize(self, points):
        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