File size: 3,667 Bytes
708dec4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import torch

from .box_head.box_head import build_roi_box_head
from .mask_head.mask_head import build_roi_mask_head
from .keypoint_head.keypoint_head import build_roi_keypoint_head


class CombinedROIHeads(torch.nn.ModuleDict):
    """

    Combines a set of individual heads (for box prediction or masks) into a single

    head.

    """

    def __init__(self, cfg, heads):
        super(CombinedROIHeads, self).__init__(heads)
        self.cfg = cfg.clone()
        if cfg.MODEL.MASK_ON and cfg.MODEL.ROI_MASK_HEAD.SHARE_BOX_FEATURE_EXTRACTOR:
            self.mask.feature_extractor = self.box.feature_extractor
        if cfg.MODEL.KEYPOINT_ON and cfg.MODEL.ROI_KEYPOINT_HEAD.SHARE_BOX_FEATURE_EXTRACTOR:
            self.keypoint.feature_extractor = self.box.feature_extractor

    def forward(self, features, proposals, targets=None, language_dict_features=None, positive_map_label_to_token=None):
        losses = {}
        detections = proposals
        if self.cfg.MODEL.BOX_ON:
            # TODO rename x to roi_box_features, if it doesn't increase memory consumption
            x, detections, loss_box = self.box(features, proposals, targets)
            losses.update(loss_box)

        if self.cfg.MODEL.MASK_ON:
            mask_features = features
            # optimization: during training, if we share the feature extractor between
            # the box and the mask heads, then we can reuse the features already computed
            if (
                    self.training
                    and self.cfg.MODEL.ROI_MASK_HEAD.SHARE_BOX_FEATURE_EXTRACTOR
            ):
                mask_features = x
            # During training, self.box() will return the unaltered proposals as "detections"
            # this makes the API consistent during training and testing
            x, detections, loss_mask = self.mask(
                mask_features, detections, targets,
                language_dict_features=language_dict_features,
                positive_map_label_to_token=positive_map_label_to_token)
            losses.update(loss_mask)

        if self.cfg.MODEL.KEYPOINT_ON:
            keypoint_features = features
            # optimization: during training, if we share the feature extractor between
            # the box and the mask heads, then we can reuse the features already computed
            if (
                    self.training
                    and self.cfg.MODEL.ROI_KEYPOINT_HEAD.SHARE_BOX_FEATURE_EXTRACTOR
            ):
                keypoint_features = x
            # During training, self.box() will return the unaltered proposals as "detections"
            # this makes the API consistent during training and testing
            x, detections, loss_keypoint = self.keypoint(keypoint_features, detections, targets)
            losses.update(loss_keypoint)
        return x, detections, losses


def build_roi_heads(cfg):
    # individually create the heads, that will be combined together
    # afterwards
    # if cfg.MODEL.RPN_ONLY:
    #     return None

    roi_heads = []
    if cfg.MODEL.BOX_ON and not cfg.MODEL.RPN_ONLY:
        roi_heads.append(("box", build_roi_box_head(cfg)))
    if cfg.MODEL.MASK_ON:
        roi_heads.append(("mask", build_roi_mask_head(cfg)))
    if cfg.MODEL.KEYPOINT_ON:
        roi_heads.append(("keypoint", build_roi_keypoint_head(cfg)))

    # combine individual heads in a single module
    if roi_heads:
        roi_heads = CombinedROIHeads(cfg, roi_heads)
    else:
        roi_heads = None

    return roi_heads