def __init__(self, config):
super(ResNet50Conv5RecFeatureExtractor, self).__init__()
# reso: [H, W]
resolution = config.MODEL.ROI_REC_HEAD.POOLER_RESOLUTION
scales = config.MODEL.ROI_REC_HEAD.POOLER_SCALES
pooler = PyramidRROIAlign(
output_size=resolution,
scales=scales,
)
self.word_margin = config.MODEL.ROI_REC_HEAD.BOXES_MARGIN
self.det_margin = config.MODEL.RRPN.GT_BOX_MARGIN
self.rescale = self.word_margin / self.det_margin
# stage = resnet.StageSpec(index=4, block_count=3, return_features=False)
'''
head = resnet.ResNetHead(
block_module=config.MODEL.RESNETS.TRANS_FUNC,
stages=(stage,),
num_groups=config.MODEL.RESNETS.NUM_GROUPS,
width_per_group=config.MODEL.RESNETS.WIDTH_PER_GROUP,
stride_in_1x1=config.MODEL.RESNETS.STRIDE_IN_1X1,
stride_init=None,
res2_out_channels=config.MODEL.RESNETS.RES2_OUT_CHANNELS,
dilation=config.MODEL.RESNETS.RES5_DILATION
)
'''
self.pooler = pooler
def __init__(self, config):
super(ResNet50Conv5ROIFeatureExtractor, self).__init__()
resolution = config.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
scales = config.MODEL.ROI_BOX_HEAD.POOLER_SCALES
sampling_ratio = config.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler = PyramidRROIAlign(
output_size=(resolution, resolution),
scales=scales,
)
stage = resnet.StageSpec(index=4, block_count=3, return_features=False)
head = resnet.ResNetHead(
block_module=config.MODEL.RESNETS.TRANS_FUNC,
stages=(stage,),
num_groups=config.MODEL.RESNETS.NUM_GROUPS,
width_per_group=config.MODEL.RESNETS.WIDTH_PER_GROUP,
stride_in_1x1=config.MODEL.RESNETS.STRIDE_IN_1X1,
stride_init=None,
res2_out_channels=config.MODEL.RESNETS.RES2_OUT_CHANNELS,
dilation=config.MODEL.RESNETS.RES5_DILATION
)
self.pooler = pooler
self.head = head
def __init__(self, cfg):
super(FPN2MLPFeatureExtractor, self).__init__()
resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
scales = cfg.MODEL.ROI_BOX_HEAD.POOLER_SCALES
sampling_ratio = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
pooler = PyramidRROIAlign(
output_size=(resolution, resolution),
scales=scales,
)
input_size = cfg.MODEL.BACKBONE.OUT_CHANNELS * resolution**2
representation_size = cfg.MODEL.ROI_BOX_HEAD.MLP_HEAD_DIM
use_gn = cfg.MODEL.ROI_BOX_HEAD.USE_GN
self.pooler = pooler
self.fc6 = make_fc(input_size, representation_size, use_gn)
self.fc7 = make_fc(representation_size, representation_size, use_gn)
def __init__(self, cfg):
"""
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(MaskRCNNFPNFeatureExtractor, 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
# pooler = Pooler(
# output_size=(resolution, resolution),
# scales=scales,
# sampling_ratio=sampling_ratio,
# )
pooler = PyramidRROIAlign(
output_size=(resolution, resolution),
scales=scales,
)
input_size = cfg.MODEL.BACKBONE.OUT_CHANNELS
self.pooler = pooler
layers = cfg.MODEL.ROI_MASK_HEAD.CONV_LAYERS
next_feature = input_size
self.blocks = []
for layer_idx, layer_features in enumerate(layers, 1):
layer_name = "mask_fcn{}".format(layer_idx)
module = Conv2d(next_feature,
layer_features,
3,
stride=1,
padding=1)
# Caffe2 implementation uses MSRAFill, which in fact
# corresponds to kaiming_normal_ in PyTorch
nn.init.kaiming_normal_(module.weight,
mode="fan_out",
nonlinearity="relu")
nn.init.constant_(module.bias, 0)
self.add_module(layer_name, module)
next_feature = layer_features
self.blocks.append(layer_name)
def __init__(self, cfg):
"""
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(MaskRCNNFPNFeatureExtractor, 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
pooler = PyramidRROIAlign(
output_size=(resolution, resolution),
scales=scales,
)
input_size = cfg.MODEL.BACKBONE.OUT_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
self.word_margin = cfg.MODEL.ROI_REC_HEAD.BOXES_MARGIN
self.det_margin = cfg.MODEL.RRPN.GT_BOX_MARGIN
self.rescale = self.word_margin / self.det_margin
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)
self.add_module(layer_name, module)
next_feature = layer_features
self.blocks.append(layer_name)