def _init_mask_head(cfg, input_shape):
in_features = cfg.MODEL.ROI_HEADS.IN_FEATURES
pooler_resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in in_features)
sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_MASK_HEAD.POOLER_TYPE
in_channels = [input_shape[f].channels for f in in_features][0]
mask_pooler = (
ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
if pooler_type
else None
)
if pooler_type:
shape = ShapeSpec(
channels=in_channels, width=pooler_resolution, height=pooler_resolution
)
else:
shape = {f: input_shape[f] for f in in_features}
return mask_pooler, build_mask_head(cfg, shape)
def __init__(self, cfg, input_shape):
super().__init__(cfg, input_shape)
# fmt: off
self.in_features = cfg.MODEL.ROI_HEADS.IN_FEATURES
pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
pooler_type = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
pooler_scales = (1.0 / input_shape[self.in_features[0]].stride,)
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
self.mask_on = cfg.MODEL.MASK_ON
# fmt: on
assert not cfg.MODEL.KEYPOINT_ON
assert len(self.in_features) == 1
self.pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.res5, out_channels = self._build_res5_block(cfg)
# @Will Lee, 2020/7/14, 通过注册和build机制将predictor解耦出去，做成cfg配置的形式
# self.box_predictor = FastRCNNOutputLayers(
# cfg, ShapeSpec(channels=out_channels, height=1, width=1)
# )
self.box_predictor = build_roi_predictor(cfg, ShapeSpec(channels=out_channels, height=pooler_resolution,
width=pooler_resolution))
if self.mask_on:
self.mask_head = build_mask_head(
cfg,
ShapeSpec(channels=out_channels, width=pooler_resolution, height=pooler_resolution),
)
def __init__(self, cfg, input_shape):
# super(Res5ROIHeads, self).__init__(cfg, input_shape) # d2 0.1.1
super(Res5ROIHeads, self).__init__(cfg) # d2 0.2.1
# added to fit d2 0.2.1
self.in_features = cfg.MODEL.ROI_HEADS.IN_FEATURES
assert len(self.in_features) == 1
# fmt: off
pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
pooler_type = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
pooler_scales = (1.0 / input_shape[self.in_features[0]].stride, )
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
self.mask_on = cfg.MODEL.MASK_ON
self.attribute_on = cfg.MODEL.BUA.ATTRIBUTE_ON
self.extract_on = cfg.MODEL.BUA.EXTRACT_FEATS
self.extractor_mode = cfg.MODEL.BUA.EXTRACTOR.MODE
# fmt: on
assert not cfg.MODEL.KEYPOINT_ON
self.pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.box2box_transform = BUABox2BoxTransform(weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS)
self.res5, out_channels = self._build_res5_block(cfg)
self.box_predictor = FastRCNNOutputLayers(
cfg, ShapeSpec(channels=out_channels, height=1, width=1)
)
if self.mask_on:
self.mask_head = build_mask_head(
cfg,
ShapeSpec(channels=out_channels, width=pooler_resolution, height=pooler_resolution),
)
if self.attribute_on:
self.attribute_predictor = AttributePredictor(cfg, out_channels)
def _init_mask_head(self, cfg, input_shape):
# fmt: off
self.mask_on = cfg.MODEL.MASK_ON
if not self.mask_on:
return
pooler_resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in self.in_features)
sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_MASK_HEAD.POOLER_TYPE
# fmt: on
in_channels = [input_shape[f].channels for f in self.in_features][0]
self.mask_pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.mask_head = build_mask_head(
cfg, ShapeSpec(channels=in_channels, width=pooler_resolution, height=pooler_resolution)
)
def __init__(self, cfg, input_shape):
super(Res5ROIHeads, self).__init__(cfg, input_shape)
assert len(self.in_features) == 1
# fmt: off
pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
pooler_type = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
pooler_scales = (1.0 / input_shape[self.in_features[0]].stride, )
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
self.mask_on = cfg.MODEL.MASK_ON
self.attribute_on = cfg.MODEL.ATTRIBUTE_ON
if self.attribute_on:
self.attribute_thre = cfg.MODEL.ATTRIBUTE_THRE
# fmt: on
assert not cfg.MODEL.KEYPOINT_ON
self.pooler = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
self.res5, out_channels = self._build_res5_block(cfg)
self.box_predictor = FastRCNNOutputLayers(
cfg, ShapeSpec(channels=out_channels, height=1, width=1)
)
if self.mask_on:
self.mask_head = build_mask_head(
cfg,
ShapeSpec(channels=out_channels, width=pooler_resolution, height=pooler_resolution),
)
if self.attribute_on:
self.attribute_predictor = AttributePredictor(cfg, out_channels)
def _init_mask_head(cls, cfg, input_shape):
if not cfg.MODEL.MASK_ON:
return {}
# fmt: off
in_features = cfg.MODEL.ROI_HEADS.IN_FEATURES
pooler_resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
pooler_scales = tuple(1.0 / input_shape[k].stride for k in in_features)
sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
pooler_type = cfg.MODEL.ROI_MASK_HEAD.POOLER_TYPE
# fmt: on
in_channels = [input_shape[f].channels for f in in_features][0]
ret = {"mask_in_features": in_features}
ret["mask_pooler"] = ROIPooler(
output_size=pooler_resolution,
scales=pooler_scales,
sampling_ratio=sampling_ratio,
pooler_type=pooler_type,
)
ret["mask_head"] = build_mask_head(
cfg, ShapeSpec(channels=in_channels, width=pooler_resolution, height=pooler_resolution)
)
return ret