def _init_box_head(self, cfg, input_shape):
# fmt: off
pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in self.in_features)
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
# fmt: on
# If StandardROIHeads is applied on multiple feature maps (as in FPN),
# then we share the same predictors and therefore the channel counts must be the same
in_channels = [input_shape[f].channels for f in self.in_features]
# Check all channel counts are equal
assert len(set(in_channels)) == 1, in_channels
in_channels = in_channels[0]
self.box_pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
# Here we split "box head" and "box predictor", which is mainly due to historical reasons.
# They are used together so the "box predictor" layers should be part of the "box head".
# New subclasses of ROIHeads do not need "box predictor"s.
self.box_head = build_box_head(
cfg, ShapeSpec(channels=in_channels, height=pooler_resolution, width=pooler_resolution)
)
self.box_predictor = FastRCNNOutputLayers(cfg, self.box_head.output_shape)
def __init__(self, cfg, input_shape):
super().__init__()
in_features = cfg.MODEL.ROI_HEADS.VISUAL_ATTENTION_HEAD.IN_FEATURES
pooler_resolution = cfg.MODEL.ROI_HEADS.VISUAL_ATTENTION_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in in_features)
sampling_ratio = cfg.MODEL.ROI_HEADS.VISUAL_ATTENTION_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_HEADS.VISUAL_ATTENTION_HEAD.POOLER_TYPE
in_channels = [input_shape[f].channels for f in in_features]
in_channels = in_channels[0]
self.num_classes = cfg.MODEL.ROI_HEADS.NUM_CLASSES
self.box_in_features = in_features
self.meta_box_pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.meta_box_head = build_box_head(cfg, ShapeSpec(channels=in_channels, height=pooler_resolution, width=pooler_resolution))
input_shape_box = self.meta_box_head.output_shape
if isinstance(input_shape_box, int): # some backward compatibility
input_shape_box = ShapeSpec(channels=input_shape_box)
input_size = input_shape_box.channels * (input_shape_box.width or 1) * (input_shape_box.height or 1)
self.input_size = input_size
self.pi_normalizer = 0.5 * input_size * np.log(2 * np.pi)
self.rank_loss_classifier = Linear(input_size, self.num_classes + 1)
nn.init.normal_(self.rank_loss_classifier.weight, std=0.01)
nn.init.constant_(self.rank_loss_classifier.bias, 0.0)
def _init_box_head(self, cfg, input_shape):
# fmt: off
pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in self.in_features)
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
self.train_on_pred_boxes = cfg.MODEL.ROI_BOX_HEAD.TRAIN_ON_PRED_BOXES
self.attribute_on = cfg.MODEL.ATTRIBUTE_ON
# fmt: on
in_channels = [input_shape[f].channels for f in self.in_features]
assert len(set(in_channels)) == 1, in_channels
in_channels = in_channels[0]
self.box_pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.box_head = build_box_head(
cfg,
ShapeSpec(
channels=in_channels, height=pooler_resolution, width=pooler_resolution
),
)
self.box_predictor = FastRCNNOutputLayers(cfg, self.box_head.output_shape)
if self.attribute_on:
self.attribute_predictor = AttributePredictor(
cfg, self.box_head.output_shape.channels
)