def __init__(self, classes, class_agnostic):
super(_RFCN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.n_reg_classes = (1 if class_agnostic else len(classes))
self.class_agnostic = class_agnostic
self.n_bbox_reg = (4 if class_agnostic else len(classes))
# loss
self.RFCN_loss_cls = 0
self.RFCN_loss_bbox = 0
# define rpn
self.RFCN_rpn = _RPN(self.dout_base_model)
self.RFCN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RFCN_psroi_cls_pool = _PSRoIPooling(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1.0 / 16.0,
group_size=7,
output_dim=self.n_classes)
self.RFCN_psroi_loc_pool = _PSRoIPooling(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1.0 / 16.0,
group_size=7,
output_dim=4 *
self.n_reg_classes)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RFCN_cls_net = nn.Conv2d(512,
self.n_classes * 7 * 7, [1, 1],
padding=0,
stride=1)
nn.init.normal(self.RFCN_cls_net.weight.data, 0.0, 0.01)
self.RFCN_bbox_net = nn.Conv2d(512,
4 * self.n_reg_classes * 7 * 7, [1, 1],
padding=0,
stride=1)
nn.init.normal(self.RFCN_bbox_net.weight.data, 0.0, 0.01)
self.RFCN_cls_score = nn.AvgPool2d((7, 7), stride=(7, 7))
self.RFCN_bbox_pred = nn.AvgPool2d((7, 7), stride=(7, 7))
def __init__(self, output_dim, group_size, spatial_scale):
super(test_PSRoIPooling, self).__init__()
self.psroi_pool = _PSRoIPooling(output_dim, group_size, spatial_scale)
def __init__(self, classes, class_agnostic):
super(_RFCN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.n_reg_classes = (1 if class_agnostic else len(classes))
self.class_agnostic = class_agnostic
self.n_bbox_reg = (4 if class_agnostic else len(classes))
# loss
self.RFCN_loss_cls = 0
self.RFCN_loss_bbox = 0
# define rpn
self.RFCN_rpn = _RPN(self.dout_base_model)
self.RFCN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RFCN_tracking_proposal_target = _TrackingProposalTargetLayer(
self.n_classes)
#self.RFCN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RFCN_psroi_cls_pool = _PSRoIPooling(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1.0 / 16.0,
group_size=7,
output_dim=self.n_classes)
self.RFCN_psroi_loc_pool = _PSRoIPooling(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1.0 / 16.0,
group_size=7,
output_dim=4 *
self.n_reg_classes)
#self.RFCN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
#self.RFCN_roi_crop = _RoICrop()
self.RFCN_cls_net = nn.Conv2d(512,
self.n_classes * 7 * 7, [1, 1],
padding=0,
stride=1)
nn.init.normal(self.RFCN_cls_net.weight.data, 0.0, 0.01)
self.RFCN_bbox_net = nn.Conv2d(512,
4 * self.n_reg_classes * 7 * 7, [1, 1],
padding=0,
stride=1)
nn.init.normal(self.RFCN_bbox_net.weight.data, 0.0, 0.01)
#self.corr_bbox_net = nn.Conv2d(1051, 4*self.n_reg_classes*7*7, [1,1], padding=0, stride=1)
#nn.init.normal(self.corr_bbox_net.weight.data, 0.0, 0.01)
self.conv3_corr_layer = Correlation(pad_size=8,
kernel_size=1,
max_displacement=8,
stride1=2,
stride2=2)
self.conv4_corr_layer = Correlation(pad_size=8,
kernel_size=1,
max_displacement=8,
stride1=1,
stride2=1)
self.conv5_corr_layer = Correlation(pad_size=8,
kernel_size=1,
max_displacement=8,
stride1=1,
stride2=1)
self.RFCN_cls_score = nn.AvgPool2d((7, 7), stride=(7, 7))
self.RFCN_bbox_pred = nn.AvgPool2d((7, 7), stride=(7, 7))
self.RFCN_tracking_pred = nn.AvgPool2d((7, 7), stride=(7, 7))