def __init__(self, config):
super(Faster_Rcnn, self).__init__()
self.config = config
self.Mean = torch.tensor(config.Mean, dtype=torch.float32)
self.num_anchor = len(config.anchor_scales) * len(config.anchor_ratios)
self.anchors = get_anchors(np.ceil(self.config.img_max / 16 + 1),
self.config.anchor_scales,
self.config.anchor_ratios)
self.PC = ProposalCreator(nms_thresh=config.roi_nms_thresh,
n_train_pre_nms=config.roi_train_pre_nms,
n_train_post_nms=config.roi_train_post_nms,
n_test_pre_nms=config.roi_test_pre_nms,
n_test_post_nms=config.roi_test_post_nms,
min_size=config.roi_min_size)
self.features = vgg16().features[:-1]
self.rpn = RPN_net(512, self.num_anchor)
self.roialign = RoIAlign((7, 7), 1 / 16., 2)
self.fast = Fast_net(config.num_cls, 512 * 7 * 7, 2048)
self.fast_2 = Fast_net(config.num_cls, 512 * 7 * 7, 2048)
self.fast_3 = Fast_net(config.num_cls, 512 * 7 * 7, 2048)
self.loc_std1 = [1. / 10, 1. / 10, 1. / 5, 1. / 5]
self.loc_std2 = [1. / 20, 1. / 20, 1. / 10, 1. / 10]
self.loc_std3 = [1. / 30, 1. / 30, 1. / 15, 1. / 15]
self.weights = [1.0, 1.0, 1.0]
def __init__(self, config):
super(Faster_Rcnn, self).__init__()
self.config = config
self.Mean = torch.tensor(config.Mean, dtype=torch.float32)
self.num_anchor = len(config.anchor_scales) * len(config.anchor_ratios)
self.anchors = get_anchors(np.ceil(self.config.img_max / 16 + 1),
self.config.anchor_scales,
self.config.anchor_ratios)
self.ATC = AnchorTargetCreator(
n_sample=config.rpn_n_sample,
pos_iou_thresh=config.rpn_pos_iou_thresh,
neg_iou_thresh=config.rpn_neg_iou_thresh,
pos_ratio=config.rpn_pos_ratio)
self.PC = ProposalCreator(nms_thresh=config.roi_nms_thresh,
n_train_pre_nms=config.roi_train_pre_nms,
n_train_post_nms=config.roi_train_post_nms,
n_test_pre_nms=config.roi_test_pre_nms,
n_test_post_nms=config.roi_test_post_nms,
min_size=config.roi_min_size)
self.PTC_1 = ProposalTargetCreator(
n_sample=config.fast_n_sample,
pos_ratio=config.fast_pos_ratio,
pos_iou_thresh=config.fast_pos_iou_thresh,
neg_iou_thresh_hi=config.fast_neg_iou_thresh_hi,
neg_iou_thresh_lo=config.fast_neg_iou_thresh_lo)
self.PTC_2 = ProposalTargetCreator(
n_sample=config.fast_n_sample,
pos_ratio=config.fast_pos_ratio,
pos_iou_thresh=0.6,
neg_iou_thresh_hi=0.6,
neg_iou_thresh_lo=config.fast_neg_iou_thresh_lo)
self.PTC_3 = ProposalTargetCreator(
n_sample=config.fast_n_sample,
pos_ratio=config.fast_pos_ratio,
pos_iou_thresh=0.7,
neg_iou_thresh_hi=0.7,
neg_iou_thresh_lo=config.fast_neg_iou_thresh_lo)
self.features = vgg16().features[:-1]
self.rpn = RPN_net(512, self.num_anchor)
self.roialign = RoIAlign((7, 7), 1 / 16., 2)
self.fast = Fast_net(config.num_cls, 512 * 7 * 7, 4096)
self.fast_2 = Fast_net(config.num_cls, 512 * 7 * 7, 4096)
self.fast_3 = Fast_net(config.num_cls, 512 * 7 * 7, 4096)
self.a = 0
self.b = 0
self.c = 0
self.d = 0
self.fast_num = 0
self.fast_num_P = 0
self.loc_std1 = [1. / 10, 1. / 10, 1. / 5, 1. / 5]
self.loc_std2 = [1. / 20, 1. / 20, 1. / 10, 1. / 10]
self.loc_std3 = [1. / 30, 1. / 30, 1. / 15, 1. / 15]
self.loss_weights = [1.0, 0.5, 0.25]
def __init__(self,
config,
block,
layers,
num_classes=1000,
zero_init_residual=False):
super(ResNet, self).__init__()
self.config = config
self.Mean = torch.tensor(config.Mean, dtype=torch.float32)
self.num_anchor = len(config.anchor_scales) * len(config.anchor_ratios)
self.anchors = get_anchors(np.ceil(self.config.img_max / 16 + 1),
self.config.anchor_scales,
self.config.anchor_ratios)
self.PC = ProposalCreator(nms_thresh=config.roi_nms_thresh,
n_train_pre_nms=config.roi_train_pre_nms,
n_train_post_nms=config.roi_train_post_nms,
n_test_pre_nms=config.roi_test_pre_nms,
n_test_post_nms=config.roi_test_post_nms,
min_size=config.roi_min_size)
self.inplanes = 64
self.conv1 = nn.Conv2d(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
self.maxpool = nn.MaxPool2d(kernel_size=3,
stride=2,
padding=0,
ceil_mode=True) # change
for i in range(2, 5):
print('layer%d' % i)
getattr(self, 'layer%d' % i)[0].conv1.stride = (2, 2)
getattr(self, 'layer%d' % i)[0].conv2.stride = (1, 1)
self.rpn = RPN_net(1024, self.num_anchor)
self.roialign = RoIAlign((14, 14), 1 / 16., 2)
self.fast = Fast_net(config.num_cls)