def __init__(self, classes, class_agnostic):
super(_HierRCNN, self).__init__()
with h5py.File('data/pretrained_model/label_vec_vrd.h5', 'r') as f:
self.label_vecs = np.array(f['label_vec'])
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()
self.order_embedding = nn.Sequential(
nn.ReLU(inplace=True), nn.Dropout(), nn.Linear(4096, 4096),
nn.ReLU(inplace=True), nn.Dropout(),
nn.Linear(4096, cfg.HIER.EMBEDDING_LENGTH))
self.order_score = _OrderSimilarity(cfg.HIER.ORDER_DISTANCE_NORM)
def __init__(self, classes, class_agnostic, compact_mode=False):
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
# self.focalloss_handle = FocalLossV4(num_class=21, alpha=0.25, gamma=2.0, balance_index=2)
# define Large Separable Convolution Layer
self.rpn = RPN(in_channels=245, f_channels=256)
self.sam = SAM(256, 245)
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.rpn_time = None
self.pre_roi_time = None
self.roi_pooling_time = None
self.subnet_time = None
self.psroiAlign = PSROIAlignhandle(1. / cfg.FEAT_STRIDE, 7, 2, 5)
self.psroiPool = PSROIPoolhandle(7, 7, 1. / cfg.FEAT_STRIDE, 7, 5)
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# = 7*2 =14
'''
# Size of the pooled region after RoI pooling
__C.POOLING_SIZE = 7 roi pooling 之后得到的特征的尺寸
CROP_RESIZE_WITH_MAX_POOL = True
'''
self.RCNN_roi_crop = _RoICrop()
def __init__(self, num_classes, num_predicates, class_agnostic):
super(_fasterRCNN, self).__init__()
self.n_classes = num_classes
self.class_agnostic = class_agnostic
self.n_preds = num_predicates
# 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 = ROIPool((cfg.POOLING_SIZE, cfg.POOLING_SIZE), 1.0 / 16.0)
self.RCNN_roi_align = ROIAlign((cfg.POOLING_SIZE, cfg.POOLING_SIZE), 1.0 / 16.0, 0)
self.Proposal_rela_layer = _Proposal_rela_layer(self.n_classes)
self.Extract_rela_featrue = _Extract_rela_feature(self.n_classes, 4096, 512)
self.linear_u_rela = FC(4096, 512)
self.linear_v_rela = FC(1536, 512)
self.linear_s_rela = FC(512, 512)
self.linear_l_rela = FC(1536, 512)
self.linear_f_rela = FC(1536, 100)
self.linear_d_rela = nn.Linear(100, 1)
self.linear_r_rela = FC(101, 512)
# rela scores predict
self.rela_cls_pred = nn.Linear(512, self.n_preds)
def __init__(self, classes, class_agnostic):
super(RFCN_head, 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_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.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.dout_base_model = 512
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, dim):
"""
Args:
dim: depth of input feature map, e.g., 512
"""
super(RPN, self).__init__()
self.rpn = _RPN(dim)
self.anchor_ratios = cfg.ANCHOR_RATIOS
self.anchor_scales = [8, 16, 32, 64, 128]
self.feat_strides = [4, 8, 16, 32, 32]
self.RPN_anchor_targets = [_AnchorTargetLayer(feat_stride=self.feat_strides[idx],
scales=scale,
ratios=self.anchor_ratios)
for idx, scale in enumerate(self.anchor_scales)]
self.RPN_proposals = [_ProposalLayer(feat_stride=self.feat_strides[idx],
scales=scale,
ratios=self.anchor_ratios)
for idx, scale in enumerate(self.anchor_scales)]
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_pool = ROIPool((cfg.POOLING_SIZE, cfg.POOLING_SIZE), 1.0/16.0)
self.RCNN_roi_align = ROIAlign((cfg.POOLING_SIZE, cfg.POOLING_SIZE), 1.0/16.0, 0)
def __init__(self):
super(_TDCNN, self).__init__()
# self.classes = classes
self.n_classes = cfg.NUM_CLASSES # 21
# loss
self.RCNN_loss_cls = 0 # 多分类损失
self.RCNN_loss_twin = 0 # 窗口回归损失
# define rpn
# self.dout_base_model=512 # (1,2000,3),(1,20,96,1,1),(1,20,96,1,1), (1), (1), (256), (1) =0
self.RCNN_rpn = _RPN(self.dout_base_model) # return rois, rpn_cls_prob, rpn_twin_pred, self.rpn_loss_cls, self.rpn_loss_twin, self.rpn_label, self.rpn_loss_mask
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_temporal_pool = _RoITemporalPooling(cfg.POOLING_LENGTH, cfg.POOLING_HEIGHT, cfg.POOLING_WIDTH, cfg.DEDUP_TWINS)
if cfg.USE_ATTENTION: # 不走这条路
self.RCNN_attention = NONLocalBlock3D(self.dout_base_model, inter_channels=self.dout_base_model)
def __init__(self, classes, class_agnostic, loss_type, pathway):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.pathway = pathway
self.n_classes = classes
self.class_agnostic = class_agnostic
self.loss_type = loss_type
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
#define fuse layer
if pathway == "two_pathway":
self.fuselayer = Fuse_twopath(self.dout_base_model)
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model, self.n_classes)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = ROIPool((cfg.POOLING_SIZE, cfg.POOLING_SIZE),
1.0 / 16.0)
self.RCNN_roi_align = ROIAlign((cfg.POOLING_SIZE, cfg.POOLING_SIZE),
1.0 / 16.0, 0)
from lib.model.rpn.rpn import _RPN
import torch
import numpy as np
if __name__ == "__main__":
base_feat = torch.randn((1, 512, 16, 16))
im_info = torch.from_numpy(np.array([[1000, 1000, 3]], dtype=np.float32))
gt_boxes = torch.randn((1, 3, 5))
num_boxes = torch.Tensor([[1, 1, 1]])
rpn = _RPN(512)
rois, rpn_loss_cls, rpn_loss_box = rpn(base_feat, im_info, gt_boxes,
num_boxes)
