def __init__(self, main_classes, sub_classes, class_agnostic):
super(_hierarchyFasterRCNN, self).__init__()
#self.classes = classes
self.main_classes = main_classes
self.sub_classes = sub_classes
self.n_sub_classes = len(sub_classes)
self.n_main_classes = len(main_classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_sub_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RFCN_psroi_pool = None
self.grid_size = cfg.POOLING_SIZE * \
2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN_OCR, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
# self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_ocr_roi_pooling = roi_pooling(2) # ocr roi_pooling
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
# rnn初始化，隐藏节点256
nh = 256
nclass = len('0123456789.') + 1
self.rnn = nn.Sequential(BidirectionalLSTM(1024, nh, nh),
BidirectionalLSTM(nh, nh, nclass))
self.ctc_critition = CTCLoss().cuda()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__() # 继承父类的__init__()方法
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
# 实例化,RPN网络(self.dout_base_model)是512,vgg16子类中定义,输入rpn的维度
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
# grid_size = 7 * 2 = 14
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
# dout_base_model = 512
self.RCNN_imageDA = _ImageDA(self.dout_base_model)
self.RCNN_instanceDA = _InstanceDA()
self.consistency_loss = torch.nn.MSELoss(size_average=False)
def __init__(self, classes, class_agnostic):
super(CoupleNet, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.box_num_classes = 1 if class_agnostic else self.n_classes
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_roi_crop = _RoICrop()
self.RCNN_psroi_pool_cls = PSRoIPool(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
spatial_scale=1/16.0, group_size=cfg.POOLING_SIZE,
output_dim=self.n_classes)
self.RCNN_psroi_pool_loc = PSRoIPool(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
spatial_scale=1/16.0, group_size=cfg.POOLING_SIZE,
output_dim=self.box_num_classes * 4)
self.avg_pooling = nn.AvgPool2d(kernel_size=cfg.POOLING_SIZE, stride=cfg.POOLING_SIZE)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_rpn_t = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.RCNN_imageDA_3 = _ImageDA(256)
self.RCNN_imageDA_4 = _ImageDA(512)
self.RCNN_imageDA = _ImageDA(self.dout_base_model)
self.RCNN_instanceDA = _InstanceDA()
def __init__(self, classes, class_agnostic, rpn_batchsize):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.rpn_batchsize = rpn_batchsize
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model, self.rpn_batchsize)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
print 'INFO: pooling size is: ', cfg.POOLING_SIZE_H, cfg.POOLING_SIZE_W
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE_H,
cfg.POOLING_SIZE_W, 1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE_H,
cfg.POOLING_SIZE_W, 1.0 / 16.0)
## wrote by Xudong Wang
self.grid_size_H = cfg.POOLING_SIZE_H * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE_H
self.grid_size_W = cfg.POOLING_SIZE_W * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE_W
## end
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic, alpha_con=None):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# crowds alpha_con
self.alpha_con = alpha_con
# label source
self.label_source = cfg.LABEL_SOURCE
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model, self.classes,
self.n_classes)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_aggregation_layer = _RCNNAggregationLayer()
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN2Fc, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(
cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_roi_align = RoIAlignAvg(
cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RFCN_psroi_pool = None
self.grid_size = cfg.POOLING_SIZE * \
2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
# attention
# self.conv_new_1 = nn.Conv2d(2048, 256, 1)
# self.fc_new_1 = nn.dense(name='fc1_new_1', num_hidden=1024)
# self.fc_new_2 = nn.dense(name='fc2_new_2', num_hidden=1024)
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, 1024)
self.nongt_dim = 256 if self.training else cfg.TEST.RPN_POST_NMS_TOP_N
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align_32 = RoIAlignAvg(cfg.POOLING_SIZE,
cfg.POOLING_SIZE, 1.0 / 32.0)
self.RCNN_roi_align_16 = RoIAlignAvg(14, 14, 1.0 / 16.0)
self.RCNN_roi_align_8 = RoIAlignAvg(28, 28, 1.0 / 8.0)
self.RCNN_roi_align_4 = RoIAlignAvg(56, 56, 1.0 / 4.0)
self.RCNN_roi_align_2 = RoIAlignAvg(112, 112, 1.0 / 2.0)
self.RCNN_roi_align_1 = RoIAlignAvg(224, 224, 1.0 / 1.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self,
classes,
class_agnostic,
meta_train,
meta_test=None,
meta_loss=None):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.meta_train = meta_train
self.meta_test = meta_test
self.meta_loss = meta_loss
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, num_ways, class_agnostic, meta_train, meta_test=None, meta_loss=None, transductive=None, visualization=None):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.meta_train = meta_train
self.meta_test = meta_test
self.meta_loss = meta_loss
self.simloss = True
self.dis_simloss = True
self.transductive = transductive
self.visualization = visualization
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.num_layers_g = 3
self.num_ways = num_ways
self.alpha = 0.5
def __init__(self, classes, class_agnostic):
super(CoupleNet, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.box_num_classes = 1 if class_agnostic else self.n_classes
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_crop = _RoICrop()
self.RCNN_psroi_pool_cls = PSRoIPool(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1 / 16.0,
group_size=cfg.POOLING_SIZE,
output_dim=self.n_classes)
self.RCNN_psroi_pool_loc = PSRoIPool(cfg.POOLING_SIZE,
cfg.POOLING_SIZE,
spatial_scale=1 / 16.0,
group_size=cfg.POOLING_SIZE,
output_dim=self.box_num_classes *
4)
self.avg_pooling = nn.AvgPool2d(kernel_size=cfg.POOLING_SIZE,
stride=cfg.POOLING_SIZE)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
def __init__(self, classes, class_agnostic, context, S_agent, T_agent, ts,
tt, select_num, candidate_num):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.select_num = select_num
self.candidate_num = candidate_num
print("self.select_num: %d self.candidate_num: %d " %
(self.select_num, self.candidate_num))
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.context = context
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.epsilon_by_epoch = lambda epoch_idx: cfg.epsilon_final + (cfg.epsilon_start - \
cfg.epsilon_final) * math.exp(-1. * epoch_idx / cfg.epsilon_decay)
self.iter_dqn = 0
self.epsilon_by_epoch_T = lambda epoch_idx: cfg.epsilon_final + (cfg.epsilon_start - \
cfg.epsilon_final) * math.exp(-1. * epoch_idx / cfg.epsilon_decay)
self.iter_dqn_T = 0
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_deform_roi_pool_1 = DeformRoIFunction(pool_height=7, pool_width=7, spatial_scale=1.0 / 16.0,
no_trans=True, trans_std=0.1,
sample_per_part=4,
output_dim=256,
group_size=1, part_size=7)
self.RCNN_deform_roi_pool_2 = DeformRoIFunction(pool_height=7, pool_width=7, spatial_scale=1.0 / 16.0,
no_trans=False, trans_std=0.1,
sample_per_part=4,
output_dim=256,
group_size=1, part_size=7)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic, lighthead=False, compact_mode=False):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.lighthead = lighthead
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define Large Separable Convolution Layer
if self.lighthead:
self.lh_mode = 'S' if compact_mode else 'L'
self.lsconv = LargeSeparableConv2d(
self.dout_lh_base_model, bias=False, bn=False, setting=self.lh_mode)
self.lh_relu = nn.ReLU(inplace=True)
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.rpn_time = None
self.pre_roi_time = None
self.roi_pooling_time = None
self.subnet_time = None
def __init__(self, classes, class_agnostic):
super(_Deconv, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
#loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.maxpool2d = nn.MaxPool2d(1, stride=2)
#define rpn
# if USE_ONE_FEATURE == 0:
self.RCNN_rpn = _RPN_Deconv(self.dout_base_model)
# else:
# self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_FPN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.maxpool2d = nn.MaxPool2d(1, stride=2)
# define rpn
self.RCNN_rpn = _RPN_FPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
# NOTE: the original paper used pool_size = 7 for cls branch, and 14 for mask branch, to save the
# computation time, we first use 14 as the pool_size, and then do stride=2 pooling for cls branch.
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_prroi = PrRoIPool2D(
cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0) ######## add precision roi pooling #####
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# define rpn
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.spaCNN = SpaConv()
self.spa_cls_score = nn.Sequential(nn.Linear(5408, 1024),
nn.LeakyReLU(), nn.Dropout(p=0.5),
nn.Linear(1024, self.n_classes))
self.obj_cls_score = nn.Sequential(nn.Linear(300, 512), nn.LeakyReLU(),
nn.Linear(512, self.n_classes))
self.obj_attention = nn.Sequential(nn.Linear(300, 512), nn.LeakyReLU(),
nn.Linear(512, 6))
def __init__(self, classes, class_agnostic, transfer):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
#transfer setting
self.transfer = transfer
if self.transfer:
self.transfer_weight = Variable(torch.Tensor([cfg.TRANSFER_WEIGHT
]).cuda(),
requires_grad=True)
self.grl = cfg.TRANSFER_GRL
self.weight = Variable(torch.zeros(0).cuda(), requires_grad=False)
self.transfer_select = cfg.TRANSFER_SELECT
self.transfer_gamma = cfg.TRANSFER_GAMMA
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
#for p in self.RCNN_rpn.parameters(): p.requires_grad = False
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
# roi pooling in vgg16
# stride = 16
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
# roi pooling in Generator Network
# stride = 2
self.RCNN_roi_pool_conv1 = _RoIPooling(cfg.POOLING_SIZE,
cfg.POOLING_SIZE, 1.0 / 2.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic, num_class=20):
super(_FPN, self).__init__()
self.num_classes = num_class
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
self.maxpool2d = nn.MaxPool2d(1, stride=2)
# define rpn
self.RCNN_rpn = _RPN_FPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
# NOTE: the original paper used pool_size = 7 for cls branch, and 14 for mask branch, to save the
# computation time, we first use 14 as the pool_size, and then do stride=2 pooling for cls branch.
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.top = nn.Sequential(
nn.Linear(in_features=12544, out_features=4096, bias=True),
nn.ReLU(inplace=True), nn.Dropout(0.5),
nn.Linear(in_features=4096, out_features=4096, bias=True),
nn.ReLU(inplace=True), nn.Dropout(0.5))
self.fc8c = nn.Linear(4096, self.num_classes)
self.fc8d = nn.Linear(4096, self.num_classes)
def __init__(self,
classes,
class_agnostic,
shrink=1,
mimic=False,
rois=None):
super(_fasterRCNN, self).__init__()
self.shrink = shrink
self.student = True if shrink >= 2 else False
self.mimic = mimic
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def _init_modules(self, load_model=True):
resnet = resnet101()
self.RCNN_base = nn.Sequential(resnet.conv1, resnet.bn1, resnet.relu,
resnet.maxpool, resnet.layer1,
resnet.layer2, resnet.layer3)
self.RCNN_top = nn.Sequential(resnet.layer4)
self.Linear_top = nn.Linear(2048, self.embedding_dim)
if load_model:
state_dict = torch.load(self.oneshot_model_path)['model']
self.load_state_dict({
k: v
for k, v in state_dict.items() if k in self.state_dict()
})
self.det_module = pseudo_siamese_det(self.det_model_path)
self.det_module.create_architecture(load_det_model=load_model)
self.det_module.training = False
self.RCNN_roi_crop = _RoICrop()
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
def __init__(self, main_classes, sub_classes, class_agnostic, casecade_type='add_score', alpha=0.5):
super(_hierarchyAttentionFasterRCNN, self).__init__()
#self.classes = classes
# type: add_score, add_prob, mul_score, mul_prob
self.casecade_type = casecade_type
self.alpha = alpha
self.main_classes = main_classes
self.sub_classes = sub_classes
self.n_sub_classes = len(sub_classes)
self.n_main_classes = len(main_classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_sub_classes)
self.RCNN_roi_pool = _RoIPooling(
cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_roi_align = RoIAlignAvg(
cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RFCN_psroi_pool = None
self.grid_size = cfg.POOLING_SIZE * \
2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
self.main2sub_idx_dict = defaultdict(list)
for key, val in sub2main_dict.items():
try:
# not all cls in dict are in this imdb
self.main2sub_idx_dict[self.main_classes.index(
val)].append(self.sub_classes.index(key))
except:
print("key:{}, val:{} may not in this imdb".format(key, val))
# attention
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, 1024)
self.nongt_dim = 300 if self.training else cfg.TEST.RPN_POST_NMS_TOP_N
self.attention_1 = attention_module_multi_head(nongt_dim=self.nongt_dim,
fc_dim=16, feat_dim=1024, index=1, group=16,
dim=(1024, 1024, 1024))
self.attention_2 = attention_module_multi_head(nongt_dim=self.nongt_dim,
fc_dim=16, feat_dim=1024, index=2, group=16,
dim=(1024, 1024, 1024))
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.n_classes = classes
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic, tb=None):
super(_OICR, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.param_groups = [[], [], [], []]
self.OICR_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 8.0)
self.OICR_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 8.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.OICR_roi_crop = _RoICrop()
self.ic_layers = []
self.tb = tb
def __init__(self, det_model_path):
super(pseudo_siamese_det, self).__init__()
self.det_model_path = det_model_path
self.dout_base_model = 1024
# self.resnet101_path = '/home/huangyucheng/MYDATA/git-cores/FasterRCNN/data/pretrained_model/resnet101_caffe.pth'
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
# self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def __init__(self, classes):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_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.RCNN_grid_gen = _AffineGridGen(self.grid_size, self.grid_size)
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# define rpn
# self.RCNN_rpn = _RPN(self.dout_base_model)
# self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
self.spa_cls_CNN = SpaConv()
self.spa_bin_CNN = SpaConv()
def __init__(self, classes, class_agnostic, K=-1):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
self.K = K # if K > 1, transform FasterRCNN to take a stack of K images as input
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model, K=self.K)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes, K=K)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__() #继承Module的舒适化
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_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 #def larger(num1, num2): return num1 if num1 > num2 else num2, this variable may be declare in other place
self.RCNN_roi_crop = _RoICrop()
def __init__(self, classes, class_agnostic):
super(_FPN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN_FPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
# NOTE: the original paper used pool_size = 7 for cls branch, and 14 for mask branch, to save the
# computation time, we first use 14 as the pool_size, and then do stride=2 pooling for cls branch.
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_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.RCNN_roi_crop = _RoICrop()
