def __init__(self):
super().__init__()
# For cache
self.mapping_to_detectron = None
self.orphans_in_detectron = None
# Backbone for feature extraction
self.Conv_Body = get_func(cfg.MODEL.CONV_BODY)()
# Region Proposal Network
if cfg.RPN.RPN_ON:
self.RPN = get_func(cfg.RPN.HEAD)(
self.Conv_Body.dim_out, self.Conv_Body.spatial_scale)
if cfg.FPN.FPN_ON:
# Only supports case when RPN and ROI min levels are the same
assert cfg.FPN.RPN_MIN_LEVEL == cfg.FPN.ROI_MIN_LEVEL
# RPN max level can be >= to ROI max level
assert cfg.FPN.RPN_MAX_LEVEL >= cfg.FPN.ROI_MAX_LEVEL
# FPN RPN max level might be > FPN ROI max level in which case we
# need to discard some leading conv blobs (blobs are ordered from
# max/coarsest level to min/finest level)
self.num_roi_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
# Retain only the spatial scales that will be used for RoI heads. `Conv_Body.spatial_scale`
# may include extra scales that are used for RPN proposals, but not for RoI heads.
self.Conv_Body.spatial_scale = self.Conv_Body.spatial_scale[-self.num_roi_levels:]
# BBOX Branch
self.Box_Head = get_func(cfg.FAST_RCNN.ROI_BOX_HEAD)(
self.RPN.dim_out, self.roi_feature_transform, self.Conv_Body.spatial_scale)
self.Box_Outs = fast_rcnn_heads.fast_rcnn_outputs(
self.Box_Head.dim_out)
# self.Prd_RCNN = copy.deepcopy(self)
# del self.Prd_RCNN.RPN
# del self.Prd_RCNN.Box_Outs
# del self.Prd_RCNN.Box_Head
# self.RelPN = relpn_heads.generic_relpn_outputs()
# rel pyramid connection
if cfg.MODEL.USE_REL_PYRAMID:
assert cfg.FPN.FPN_ON
self.RelPyramid = rel_pyramid_module.rel_pyramid_module(self.num_roi_levels)
self._init_modules()
def __init__(self):
super().__init__()
# For cache
self.mapping_to_detectron = None
self.orphans_in_detectron = None
# Backbone for feature extraction
self.Conv_Body = get_func(cfg.MODEL.CONV_BODY)()
# Region Proposal Network
if cfg.RPN.RPN_ON:
self.RPN = rpn_heads.generic_rpn_outputs(
self.Conv_Body.dim_out, self.Conv_Body.spatial_scale)
if cfg.FPN.FPN_ON:
# Only supports case when RPN and ROI min levels are the same
assert cfg.FPN.RPN_MIN_LEVEL == cfg.FPN.ROI_MIN_LEVEL
# RPN max level can be >= to ROI max level
assert cfg.FPN.RPN_MAX_LEVEL >= cfg.FPN.ROI_MAX_LEVEL
# FPN RPN max level might be > FPN ROI max level in which case we
# need to discard some leading conv blobs (blobs are ordered from
# max/coarsest level to min/finest level)
self.num_roi_levels = cfg.FPN.ROI_MAX_LEVEL - cfg.FPN.ROI_MIN_LEVEL + 1
# Retain only the spatial scales that will be used for RoI heads. `Conv_Body.spatial_scale`
# may include extra scales that are used for RPN proposals, but not for RoI heads.
self.Conv_Body.spatial_scale = self.Conv_Body.spatial_scale[
-self.num_roi_levels:]
# BBOX Branch
self.Box_Head = get_func(cfg.FAST_RCNN.ROI_BOX_HEAD)(
self.RPN.dim_out, self.roi_feature_transform,
self.Conv_Body.spatial_scale)
self.Box_Outs = fast_rcnn_heads.fast_rcnn_outputs(
self.Box_Head.dim_out)
self.ori_embed = get_ort_embeds(cfg.MODEL.NUM_CLASSES, 200)
# rel pyramid connection
if cfg.MODEL.USE_REL_PYRAMID:
assert cfg.FPN.FPN_ON
self.RelPyramid = rel_pyramid_module.rel_pyramid_module(
self.num_roi_levels)
# RelPN
self.RelPN = relpn_heads.generic_relpn_outputs()
self.Box_Head_sg = copy.deepcopy(self.Box_Head)
self.Box_Head_prd = get_func(cfg.FAST_RCNN.ROI_BOX_HEAD_PRD)(
self.RPN.dim_out, self.roi_feature_transform,
self.Conv_Body.spatial_scale)
self.union_mask = reldn_heads.union_mask(self.RPN.dim_out)
self.obj_dim = self.Box_Head.dim_out
self.merge_obj_feats = Merge_OBJ_Feats(self.obj_dim, 200, 512)
self.obj_mps1 = Message_Passing4OBJ(512)
self.obj_mps2 = Message_Passing4OBJ(512)
self.ObjClassifier = nn.Linear(512, cfg.MODEL.NUM_CLASSES)
self.EdgePN = relpn_heads.single_scale_pairs_pn_outputs(False)
self.get_phr_feats = nn.Linear(self.obj_dim, 512)
self.sbj_map = nn.Linear(self.obj_dim + 200 + 5, self.obj_dim)
self.sbj_map.weight = torch.nn.init.xavier_normal_(self.sbj_map.weight,
gain=1.0)
self.obj_map = nn.Linear(self.obj_dim + 200 + 5, self.obj_dim)
self.obj_map.weight = torch.nn.init.xavier_normal_(self.obj_map.weight,
gain=1.0)
if cfg.MODEL.USE_BG:
self.num_prd_classes = cfg.MODEL.NUM_PRD_CLASSES + 1
else:
self.num_prd_classes = cfg.MODEL.NUM_PRD_CLASSES
self.rel_compress = nn.Linear(self.obj_dim, self.num_prd_classes)
self.rel_compress.weight = torch.nn.init.xavier_normal_(
self.rel_compress.weight, gain=1.0)
if cfg.MODEL.USE_FREQ_BIAS:
# Assume we are training/testing on only one dataset
if len(cfg.TRAIN.DATASETS):
self.freq_bias = FrequencyBias_Fix(cfg.TRAIN.DATASETS[0])
else:
self.freq_bias = FrequencyBias_Fix(cfg.TEST.DATASETS[0])
self._init_modules()