本文整理匯總了Python中vgg.VGG16屬性的典型用法代碼示例。如果您正苦於以下問題：Python vgg.VGG16屬性的具體用法？Python vgg.VGG16怎麽用？Python vgg.VGG16使用的例子？那麽, 這裏精選的屬性代碼示例或許可以為您提供幫助。您也可以進一步了解該屬性所在類vgg的用法示例。
在下文中一共展示了vgg.VGG16屬性的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: __init__
# 需要導入模塊: import vgg [as 別名]
# 或者: from vgg import VGG16 [as 別名]
def __init__(self, n_classes):
super(RUN300, self).__init__()
self.n_classes = n_classes
self.Base = VGG16()
self.Extra = nn.Sequential(OrderedDict([
('extra1_1', nn.Conv2d(1024, 256, 1)),
('extra1_2', nn.Conv2d(256, 512, 3, padding=1, stride=2)),
('extra2_1', nn.Conv2d(512, 128, 1)),
('extra2_2', nn.Conv2d(128, 256, 3, padding=1, stride=2)),
('extra3_1', nn.Conv2d(256, 128, 1)),
('extra3_2', nn.Conv2d(128, 256, 3)),
('extra4_1', nn.Conv2d(256, 128, 1)),
('extra4_2', nn.Conv2d(128, 256, 3))]))
self.pred_layers = ['conv4_3', 'conv7', 'extra1_2', 'extra2_2', 'extra3_2','extra4_2']
n_channels = [512, 1024, 512, 256, 256, 256]
self.L2Norm = nn.ModuleList([L2Norm(512, 20)])
self.l2norm_layers = ['conv4_3']
# Multi-Way Residual Blocks
self.ResBlocks = nn.ModuleList()
for i in range(len(n_channels) - 1):
self.ResBlocks.append(
ThreeWay(n_channels[i], n_channels[i+1], self.config['grids'][i], self.config['grids'][i+1],
out_channels=256))
self.ResBlocks.append(TwoWay(n_channels[-1], out_channels=256))
# Unified Prediction Module
n_boxes = len(self.config['aspect_ratios']) + 1
#self.Loc = nn.Conv2d(256, n_boxes * 4, 3, padding=1)
#self.Conf = nn.Conv2d(256, n_boxes * (self.n_classes+1), 3, padding=1)
self.Loc = nn.Sequential(
nn.Conv2d(256, 256, 1),
nn.ReLU(inplace=True),
nn.Conv2d(256, n_boxes * 4, 3, padding=1))
self.Conf = nn.Sequential(
nn.Conv2d(256, 256, 1),
nn.ReLU(inplace=True),
nn.Conv2d(256, n_boxes * (self.n_classes+1), 3, padding=1)) 示例2: __init__
# 需要導入模塊: import vgg [as 別名]
# 或者: from vgg import VGG16 [as 別名]
def __init__(self, n_classes=1):
super().__init__()
self.n_classes = n_classes
self.rolling_times = 4
self.rolling_ratio = 0.075
self.Base = VGG16()
self.Extra = nn.Sequential(OrderedDict([
('extra1_1', nn.Conv2d(1024, 256, 1)),
('extra1_2', nn.Conv2d(256, 256, 3, padding=1, stride=2)),
('extra2_1', nn.Conv2d(256, 128, 1)),
('extra2_2', nn.Conv2d(128, 256, 3, padding=1, stride=2)),
('extra3_1', nn.Conv2d(256, 128, 1)),
('extra3_2', nn.Conv2d(128, 256, 3, padding=1, stride=2))]))
self.pred_layers = ['conv4_3', 'conv7', 'extra1_2', 'extra2_2', 'extra3_2']
self.L2Norm = nn.ModuleList([L2Norm(512, 20)])
self.l2norm_layers = ['conv4_3']
# intermediate layers
self.Inter = nn.ModuleList([
nn.Sequential(nn.Conv2d(512, 256, 3, padding=1), nn.ReLU(inplace=True))
nn.Sequential(nn.Conv2d(1024, 256, 3, padding=1), nn.ReLU(inplace=True))
nn.Sequential(),
nn.Sequential(),
nn.Sequential()])
n_channels = [256, 256, 256, 256, 256]
# Recurrent Rolling
self.RollLeft = nn.ModuleList([])
self.RollRight = nn.ModuleList([])
self.Roll = nn.ModuleList([])
for i in range(len(n_channels)):
n_out = int(n_channels[i] * self.rolling_ratio)
if i > 0:
self.RollLeft.append( nn.Sequential(
nn.Conv2d(n_channels[i-1], n_out, 1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, ceil_mode=True)))
if i < len(n_channels) - 1:
self.RollRight.append( nn.Sequential(
nn.Conv2d(n_channels[i+1], n_out, 1),
nn.Relu(inplace=True),
nn.ConvTranspose2d(n_out, n_out, kernel_size=4, stride=2, padding=1)))
n_out = n_out * (int(i>0) + int(i<len(n_channels)-1))
self.Roll.append(nn.Sequential(
nn.Conv2d(n_channels[i] + n_out, n_channels[i], 1),
nn.ReLU(inplace=True)))
# Prediction
self.Loc = nn.ModuleList([])
self.Conf = nn.ModuleList([])
for i in range(len(n_channels)):
n_boxes = len(self.config['aspect_ratios'][i]) + 1
self.Loc.append(nn.Conv2d(n_channels[i], n_boxes * 4, 3, padding=1))
self.Conf.append(nn.Conv2d(n_channels[i], n_boxes * (self.n_classes + 1), 3, padding=1))