def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = 300
# 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()
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
python类v2()的实例源码
def __init__(self, base, extras, head, num_classes):
super(SSD, self).__init__()
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.num_priors = self.priors.size(0)
self.size = 300
# 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().cuda()
# self.detect = Detect(num_classes, 0, 200, 0.001, 0.45)
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = 300
# 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()
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = 300
# 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()
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
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']
def __init__(self, num_classes, bkg_label, top_k, conf_thresh, nms_thresh):
self.num_classes = num_classes
self.background_label = bkg_label
self.top_k = top_k
# Parameters used in nms.
self.nms_thresh = nms_thresh
if nms_thresh <= 0:
raise ValueError('nms_threshold must be non negative.')
self.conf_thresh = conf_thresh
self.variance = cfg['variance']
self.output = torch.zeros(1, self.num_classes, self.top_k, 5)
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']
def __init__(self,num_classes,overlap_thresh,prior_for_matching,bkg_label,neg_mining,neg_pos,neg_overlap,encode_target):
super(MultiBoxLoss, self).__init__()
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']
def __init__(self, num_classes, bkg_label, top_k, conf_thresh, nms_thresh):
self.num_classes = num_classes
self.background_label = bkg_label
self.top_k = top_k
# Parameters used in nms.
self.nms_thresh = nms_thresh
if nms_thresh <= 0:
raise ValueError('nms_threshold must be non negative.')
self.conf_thresh = conf_thresh
self.variance = cfg['variance']
self.output = torch.zeros(1, self.num_classes, self.top_k, 5)
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']
def __init__(self, num_classes, bkg_label, top_k, conf_thresh, nms_thresh):
self.num_classes = num_classes
self.background_label = bkg_label
self.top_k = top_k
# Parameters used in nms.
self.nms_thresh = nms_thresh
if nms_thresh <= 0:
raise ValueError('nms_threshold must be non negative.')
self.conf_thresh = conf_thresh
self.variance = cfg['variance']
self.output = torch.zeros(1, self.num_classes+1, self.top_k, 5)
def forward(self):
mean = []
# TODO merge these
if self.version == 'v2':
for k, f in enumerate(self.feature_maps):
for i, j in product(range(f), repeat=2):
f_k = self.image_size / self.steps[k]
# unit center x,y
cx = (j + 0.5) / f_k
cy = (i + 0.5) / f_k
# aspect_ratio: 1
# rel size: min_size
s_k = self.min_sizes[k]/self.image_size
mean += [cx, cy, s_k, s_k]
# aspect_ratio: 1
# rel size: sqrt(s_k * s_(k+1))
s_k_prime = sqrt(s_k * (self.max_sizes[k]/self.image_size))
mean += [cx, cy, s_k_prime, s_k_prime]
# rest of aspect ratios
for ar in self.aspect_ratios[k]:
mean += [cx, cy, s_k*sqrt(ar), s_k/sqrt(ar)]
mean += [cx, cy, s_k/sqrt(ar), s_k*sqrt(ar)]
else:
# original version generation of prior (default) boxes
for i, k in enumerate(self.feature_maps):
step_x = step_y = self.image_size/k
for h, w in product(range(k), repeat=2):
c_x = ((w+0.5) * step_x)
c_y = ((h+0.5) * step_y)
c_w = c_h = self.min_sizes[i] / 2
s_k = self.image_size # 300
# aspect_ratio: 1,
# size: min_size
mean += [(c_x-c_w)/s_k, (c_y-c_h)/s_k,
(c_x+c_w)/s_k, (c_y+c_h)/s_k]
if self.max_sizes[i] > 0:
# aspect_ratio: 1
# size: sqrt(min_size * max_size)/2
c_w = c_h = sqrt(self.min_sizes[i] *
self.max_sizes[i])/2
mean += [(c_x-c_w)/s_k, (c_y-c_h)/s_k,
(c_x+c_w)/s_k, (c_y+c_h)/s_k]
# rest of prior boxes
for ar in self.aspect_ratios[i]:
if not (abs(ar-1) < 1e-6):
c_w = self.min_sizes[i] * sqrt(ar)/2
c_h = self.min_sizes[i] / sqrt(ar)/2
mean += [(c_x-c_w)/s_k, (c_y-c_h)/s_k,
(c_x+c_w)/s_k, (c_y+c_h)/s_k]
# back to torch land
output = torch.Tensor(mean).view(-1, 4)
if self.clip:
output.clamp_(max=1, min=0)
return output
