def __init__(self, cfg, in_channels):
super(MaskIoUFeatureExtractor, self).__init__()
layers = cfg.MODEL.ROI_MASKIOU_HEAD.CONV_LAYERS
resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION // 2
input_features = in_channels + 1
fc_input_size = layers[0] * resolution * resolution
self.blocks = []
stride = 1
for layer_idx, layer_features in enumerate(layers, 1):
layer_name = "maskiou_fcn{}".format(layer_idx)
if layer_idx == len(layers):
stride = 2
module = make_conv3x3(input_features,
layer_features,
stride=stride)
setattr(self, layer_name, module)
input_features = layer_features
self.blocks.append(layer_name)
self.maskiou_fc1 = nn.Linear(fc_input_size, 1024)
self.maskiou_fc2 = nn.Linear(1024, 1024)
for l in [self.maskiou_fc1, self.maskiou_fc2]:
nn.init.kaiming_uniform_(l.weight, a=1)
nn.init.constant_(l.bias, 0)
def __init__(self, cfg, in_channels):
"""
Arguments:
num_classes (int): number of output classes
input_size (int): number of channels of the input once it's flattened
representation_size (int): size of the intermediate representation
"""
super(MaskRCNNFPNSpatialAttentionFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_MASK_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
lvl_map_func = cfg.MODEL.ROI_MASK_HEAD.LEVEL_MAP_FUNCTION
self.maskiou = cfg.MODEL.MASKIOU_ON
pooler = Pooler(output_size=(resolution, resolution),
scales=scales,
sampling_ratio=sampling_ratio,
lvl_map_func=lvl_map_func)
input_size = in_channels
self.pooler = pooler
use_gn = cfg.MODEL.ROI_MASK_HEAD.USE_GN
layers = cfg.MODEL.ROI_MASK_HEAD.CONV_LAYERS
dilation = cfg.MODEL.ROI_MASK_HEAD.DILATION
#spatial attention module
self.spatialAtt = SpatialAttention()
self.num_pooler = len(scales)
next_feature = input_size
self.blocks = []
for layer_idx, layer_features in enumerate(layers, 1):
layer_name = "mask_fcn{}".format(layer_idx)
module = make_conv3x3(next_feature,
layer_features,
dilation=dilation,
stride=1,
use_gn=use_gn)
setattr(self, layer_name, module)
next_feature = layer_features
self.blocks.append(layer_name)
self.out_channels = layer_features