本文整理汇总了Python中data.coco方法的典型用法代码示例。如果您正苦于以下问题：Python data.coco方法的具体用法？Python data.coco怎么用？Python data.coco使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类data的用法示例。
在下文中一共展示了data.coco方法的9个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, phase, size, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
if(size==300):
self.cfg = (coco, voc300)[num_classes == 21]
else:
self.cfg = (coco, voc512)[num_classes == 21]
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = size
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
if phase == 'test':
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) 示例2: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, num_classes, overlap_thresh, prior_for_matching,
bkg_label, neg_mining, neg_pos, neg_overlap, encode_target,
use_gpu=True, theta=0.01, use_ARM=False):
super(RefineDetMultiBoxLoss, self).__init__()
self.use_gpu = use_gpu
self.num_classes = num_classes
self.threshold = overlap_thresh
self.background_label = bkg_label
self.encode_target = encode_target
self.use_prior_for_matching = prior_for_matching
self.do_neg_mining = neg_mining
self.negpos_ratio = neg_pos
self.neg_overlap = neg_overlap
self.variance = cfg['variance']
self.theta = theta
self.use_ARM = use_ARM 示例3: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, phase,model, size, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = (coco, voc)[num_classes == 21]
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), requires_grad=True)
self.size = size
self.model=model
# SSD network
self.base = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm( 512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
if phase == 'test':
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) 示例4: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, phase, size, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = (coco, voc)[num_classes == 21]
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = size
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
if phase == 'test':
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) 示例5: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, num_classes, overlap_thresh, prior_for_matching,
bkg_label, neg_mining, neg_pos, neg_overlap, encode_target,
use_gpu=True, theta=0.01, use_ARM=False):
super(softRefineDetMultiBoxLoss, self).__init__()
self.use_gpu = use_gpu
self.num_classes = num_classes
self.threshold = overlap_thresh
self.background_label = bkg_label
self.encode_target = encode_target
self.use_prior_for_matching = prior_for_matching
self.do_neg_mining = neg_mining
self.negpos_ratio = neg_pos
self.neg_overlap = neg_overlap
self.variance = cfg['variance']
self.theta = theta
self.use_ARM = use_ARM 示例6: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, num_classes, overlap_thresh, prior_for_matching,
bkg_label, neg_mining, neg_pos, neg_overlap, encode_target,
use_gpu=True, theta=0.01, use_ARM=False):
super(RPRefineDetMultiBoxLoss, self).__init__()
self.use_gpu = use_gpu
self.num_classes = num_classes
self.threshold = overlap_thresh
self.background_label = bkg_label
self.encode_target = encode_target
self.use_prior_for_matching = prior_for_matching
self.do_neg_mining = neg_mining
self.negpos_ratio = neg_pos
self.neg_overlap = neg_overlap
self.variance = cfg['variance']
self.theta = theta
self.use_ARM = use_ARM 示例7: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, phase, size, base, extras, head, num_classes):
super(SSD_CON, self).__init__()
self.phase = phase
self.num_classes = num_classes
if(size==300):
self.cfg = (coco, voc300)[num_classes == 21]
else:
self.cfg = (coco, voc512)[num_classes == 21]
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = size
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.softmax = nn.Softmax(dim=-1)
if phase == 'test':
# self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45) 示例8: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, num_classes, overlap_thresh, prior_for_matching,
bkg_label, neg_mining, neg_pos, neg_overlap, encode_target,
use_gpu=True):
super(MultiBoxLoss, self).__init__()
self.use_gpu = use_gpu
self.num_classes = num_classes
self.threshold = overlap_thresh
self.background_label = bkg_label
self.encode_target = encode_target
self.use_prior_for_matching = prior_for_matching
self.do_neg_mining = neg_mining
self.negpos_ratio = neg_pos
self.neg_overlap = neg_overlap
self.variance = cfg['variance'] 示例9: __init__
# 需要导入模块: import data [as 别名]
# 或者: from data import coco [as 别名]
def __init__(self, use_gpu=True, sigma=0.):
super(RepulsionLoss, self).__init__()
self.use_gpu = use_gpu
self.variance = cfg['variance']
self.sigma = sigma
# TODO