def forward(self, pred, prior_box, targets):
loc_data, conf_data = pred
batch_num = loc_data.size(0)
prior_box_num = (prior_box.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(batch_num, prior_box_num, 4)
conf_t = torch.LongTensor(batch_num, prior_box_num)
for idx in range(batch_num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = prior_box.data
match(self.threshold, truths, defaults, self.variance, labels, loc_t, conf_t, idx)
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
pos = conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(batch_num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predict, truth, weight=None):
if self.mixup:
assert predict.shape[0] == truth.shape[0] == weight.shape[0]
else:
assert predict.shape[0] == truth.shape[0]
if self.softmax_focal:
# using OHEM and focal loss with CE
soft_score = focal_sum_exp(predict)
pro = self.alpha * (1 - soft_score)**self.gamma
cmsloss = (log_sum_exp(predict) - predict.gather(
1, truth.view(-1, 1))) * pro.gather(1, truth.view(-1, 1))
elif self.label_smooth:
cmsloss = (log_sum_exp(predict, label_smooth=True) * truth).sum(
1, keepdim=True)
else:
cmsloss = log_sum_exp(predict) - predict.gather(
1, truth.view(-1, 1))
if self.mixup:
cmsloss = cmsloss * weight
if self.size_average:
return cmsloss.mean()
else:
return cmsloss.sum()
def run(self, bbox_regressions_list, classifications_list, priors,
all_priors, targets):
cls_mask_list = []
loc_mask_list = []
for i in range(len(bbox_regressions_list)):
prior = priors[i].cuda()
bbox_regression = bbox_regressions_list[i]
conf_data = classifications_list[i]
num = bbox_regression.size(0)
num_priors = int(prior.size(0))
mask_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data
defaults = prior.data
match(truths, defaults, all_priors.cuda().data, mask_t, idx)
if GPU:
mask_t = mask_t.cuda()
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, mask_t.view(-1, 1))
zeros = torch.tensor(0).cuda()
pos = mask_t > zeros
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos,
max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
cls_mask = torch.sum(
(pos + neg).view(num, -1, self.num_anchors), 2) > 0
loc_mask = torch.sum(pos.view(num, -1, self.num_anchors), 2) > 0
cls_mask_list.append(cls_mask.detach())
loc_mask_list.append(loc_mask.detach())
return loc_mask_list, cls_mask_list
def forward(self, predictions, targets):
loc_data, conf_data = predictions
num_images = loc_data.size(0)
num_priors = (self.priors.size(0))
loc_t = torch.Tensor(num_images, num_priors, 4)
conf_t = torch.LongTensor(num_images, num_priors)
priors = self.priors.data
for idx in range(num_images):
gt_boxes = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
loc, conf = boxlib.match(gt_boxes, priors, labels, self.args.overlap_th, self.args.variance)
loc_t[idx], conf_t[idx] = loc, conf
if self.args.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# calculate location loss
pos = conf_t > 0
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data) # (n_images, n_priors, 4)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum') # (cx, cy, w, h)
# hard negative mining
batch_conf = conf_data.view(-1, self.args.num_classes) # conf_data.shape = (n_images, n_priors, 2)
loss_c = boxlib.log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1)) # calculate the -log(softmax()) = - x_y + log_sum_exp
loss_c[pos.view(-1, 1)] = 0
loss_c = loss_c.view(num_images, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.args.np_ratio * num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
scores = conf_data[(pos_idx + neg_idx).gt(0)].view(-1, self.args.num_classes)
np_gty = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(scores, np_gty, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + α * Lloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
#import pdb; pdb.set_trace()
loc_data, conf_data, landm_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data
labels = targets[idx][:, -1].data
landms = targets[idx][:, 4:14].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels, landms, loc_t, conf_t, landm_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
zeros = torch.tensor(0).cuda()
# landm Loss (Smooth L1)
# Shape: [batch,num_priors,10]
pos1 = conf_t > zeros
num_pos_landm = pos1.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
#import pdb
#pdb.set_trace()
landm_p = landm_data[pos_idx1].view(-1, 10)[:,:4]
landm_t1 = landm_t[pos_idx1].view(-1, 10)[:,:4]
#s1 = torch.ones(1,2)
#s2 = torch.ones(1,4)*3
#s = torch.cat([s1,s2],dim=-1).cuda()
loss_landm = self.wingloss(landm_p, landm_t1)
#loss_landm = F.smooth_l1_loss(landm_p, landm_t1, reduction='sum')
one = torch.tensor(1).cuda()
pos_mafa = conf_t == one
num_pos_landm2 = pos_mafa.long().sum(1, keepdim=True)
N2 = max(num_pos_landm2.data.sum().float(), 1)
pos_idx2 = pos_mafa.unsqueeze(pos_mafa.dim()).expand_as(landm_data)
landm_p_mafa = landm_data[pos_idx2].view(-1, 10)[:,4:]
landm_t1_mafa = landm_t[pos_idx2].view(-1, 10)[:,4:]
s1 = torch.ones(1,2)
s2 = torch.ones(1,4)*3
s = torch.cat([s1,s2],dim=-1).cuda()
loss_landm_mafa = self.wingloss(landm_p_mafa*s,landm_t1_mafa*s)
#loss_landm_mafa = F.smooth_l1_loss(landm_p_mafa*s,landm_t1_mafa*s,reduction='sum')
#loss_landm = self.wingloss(landm_p*s, landm_t*s)
#loss_landm = self.adaptivewingloss(landm_p, landm_t)
pos = conf_t != zeros
conf_t[pos] = 1
# eye landmark loss
#pos2 = pos.unsqueeze(pos.dim()).expand_as(landm_data)
#lm_eye_p = landm_data[pos2].view(-1, 10)[:,:4]
#lm_eye_t = landm_t[pos2].view(-1, 10)[:,:4]
#loss_landm_eye = F.smooth_l1_loss(lm_eye_p, lm_eye_t, reduction='sum')
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
one = torch.tensor(1).cuda()
#import pdb
#pdb.set_trace()
tmp = torch.where(targets_weighted==one,torch.tensor(0.1).cuda(),torch.tensor(0.0).cuda())
conf_p[:,1] = conf_p[:,1] - tmp
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_landm /= N1
loss_landm_mafa /= N2
loss_lm = loss_landm + loss_landm_mafa
return loss_l, loss_c, loss_lm
def forward(self, predictions, targets, big_ssd_preds=None, distill_mask=None):
loc_data, conf_data, priors = predictions
if self._enable_distill:
assert big_ssd_preds is not None
num = loc_data.size(0)
priors = priors[:loc_data.size(1), :]
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.zeros(num, num_priors, 4)
conf_t = torch.zeros(num, num_priors, dtype=torch.long)
best_priors_msk = []
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
if self.use_half:
truths = truths.half()
defaults = priors.data
pmsk = match(self.threshold, truths, defaults, self.variance, labels, loc_t, conf_t, idx)
best_priors_msk.append(pmsk)
best_priors_msk = torch.stack(best_priors_msk)
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t.requires_grad = False
conf_t.requires_grad = False
pos = conf_t > 0
assert (pos & best_priors_msk == best_priors_msk).min().item() == 1
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
loc_p = loc_data[pos].view(-1, 4)
loc_t = loc_t[pos].view(-1, 4)
pos_idx_l = pos
msk = best_priors_msk[pos]
loss_l = F.smooth_l1_loss(loc_p[~msk], loc_t[~msk], reduction='sum')
loss_l += self.bpw * F.smooth_l1_loss(loc_p[msk], loc_t[msk], reduction='sum')
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c = loss_c.view(pos.size(0), pos.size(1))
loss_c[pos] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
chosen_idx = pos | neg
conf_p = conf_data[chosen_idx].view(-1, self.num_classes)
targets_weighted = conf_t[pos | neg]
msk = best_priors_msk[pos | neg]
loss_c = F.cross_entropy(conf_p[~msk], targets_weighted[~msk], reduction='sum')
loss_c += self.bpw * F.cross_entropy(conf_p[msk], targets_weighted[msk], reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = pos.sum() + best_priors_msk.sum() * (self.bpw - 1.)
loss_l /= N
loss_c /= N
if self._enable_distill:
big_loc_data, big_conf_data, _ = big_ssd_preds
inv_temperature = 1 / 1.
# 大网络和小网络的 prior boxes 数量不同。vgg-lite小网络没有对 38 * 38 的识别。
if distill_mask is not None:
big_loc_data = big_loc_data[:, distill_mask]
big_conf_data = big_conf_data[:, distill_mask]
big_conf_p = big_conf_data[chosen_idx].view(-1, self.num_classes)
y_softmax = F.log_softmax(conf_p * inv_temperature, dim=1)
y_big_softmax = F.softmax(big_conf_p, dim=1)
big_loc_p = big_loc_data[pos_idx_l].view(-1, 4)
# same as loss_c and loss_l
loss_c_distill = -(y_big_softmax * y_softmax).sum(dim=1).sum()
loss_l_distill = F.smooth_l1_loss(loc_p, big_loc_p, reduction='sum')
loss_c_distill /= N
loss_l_distill /= N
return loss_l, loss_c, loss_c_distill, loss_l_distill
return loss_l, loss_c
def forward(self, predictions, targets):
#--------------------------------------------------#
# 取出预测结果的三个值：回归信息，置信度，先验框
#--------------------------------------------------#
loc_data, conf_data, priors = predictions
#--------------------------------------------------#
# 计算出batch_size和先验框的数量
#--------------------------------------------------#
num = loc_data.size(0)
num_priors = (priors.size(0))
#--------------------------------------------------#
# 创建一个tensor进行处理
#--------------------------------------------------#
loc_t = torch.zeros(num, num_priors, 4).type(torch.FloatTensor)
conf_t = torch.zeros(num, num_priors).long()
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
priors = priors.cuda()
for idx in range(num):
# 获得真实框与标签
truths = targets[idx][:, :-1]
labels = targets[idx][:, -1]
if (len(truths) == 0):
continue
# 获得先验框
defaults = priors
#--------------------------------------------------#
# 利用真实框和先验框进行匹配。
# 如果真实框和先验框的重合度较高，则认为匹配上了。
# 该先验框用于负责检测出该真实框。
#--------------------------------------------------#
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
#--------------------------------------------------#
# 转化成Variable
# loc_t (num, num_priors, 4)
# conf_t (num, num_priors)
#--------------------------------------------------#
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
# 所有conf_t>0的地方，代表内部包含物体
pos = conf_t > 0
#--------------------------------------------------#
# 求和得到每一个图片内部有多少正样本
# num_pos (num, )
#--------------------------------------------------#
num_pos = pos.sum(dim=1, keepdim=True)
#--------------------------------------------------#
# 取出所有的正样本，并计算loss
# pos_idx (num, num_priors, 4)
#--------------------------------------------------#
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
#--------------------------------------------------#
# batch_conf (num * num_priors, num_classes)
# loss_c (num, num_priors)
#--------------------------------------------------#
batch_conf = conf_data.view(-1, self.num_classes)
# 这个地方是在寻找难分类的先验框
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
loss_c = loss_c.view(num, -1)
# 难分类的先验框不把正样本考虑进去，只考虑难分类的负样本
loss_c[pos] = 0
#--------------------------------------------------#
# loss_idx (num, num_priors)
# idx_rank (num, num_priors)
#--------------------------------------------------#
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
#--------------------------------------------------#
# 求和得到每一个图片内部有多少正样本
# num_pos (num, )
# neg (num, num_priors)
#--------------------------------------------------#
num_pos = pos.long().sum(1, keepdim=True)
# 限制负样本数量
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
num_neg[num_neg.eq(0)] = self.negatives_for_hard
neg = idx_rank < num_neg.expand_as(idx_rank)
#--------------------------------------------------#
# 求和得到每一个图片内部有多少正样本
# pos_idx (num, num_priors, num_classes)
# neg_idx (num, num_priors, num_classes)
#--------------------------------------------------#
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
# 选取出用于训练的正样本与负样本，计算loss
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
N = torch.max(num_pos.data.sum(), torch.ones_like(num_pos.data.sum()))
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets, conf_target_stand_dist):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
bin_conf: torch.size(batch_size,num_priors,2)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data, bin_conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
bin_conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = priors.data
match_3_terms(self.threshold, truths, defaults, self.variance,
labels, loc_t, conf_t, bin_conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
bin_conf_t = bin_conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
bin_conf_t = Variable(bin_conf_t, requires_grad=False)
pos = bin_conf_t > 0
fake_pos = pos + (conf_t < 0)
conf_t[conf_t < 0] = 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max binary_conf across batch for hard negative mining
batch_bin_conf = bin_conf_data.view(-1, 2)
loss_bin = log_sum_exp(batch_bin_conf) - batch_bin_conf.gather(
1, bin_conf_t.view(-1, 1))
# Hard Negative Mining
loss_bin[pos.view(-1, 1)] = 0 # filter out pos boxes for now
#loss_bin[fake_pos.view(-1, 1)] = 0 # filter out fake pos boxes for now
loss_bin = loss_bin.view(num, -1)
_, loss_idx = loss_bin.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
neg_binary = neg
'''
loss_bin = loss_bin.view(-1,1)
loss_bin[fake_pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_bin = loss_bin.view(num, -1)
_, loss_idx = loss_bin.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# neg_binary = neg
'''
# Binary confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(bin_conf_data)
neg_idx = neg.unsqueeze(2).expand_as(bin_conf_data)
bin_conf_p = bin_conf_data[(pos_idx + neg_idx).gt(0)].view(-1, 2)
targets_weighted = bin_conf_t[(pos + neg).gt(0)]
loss_bin = F.cross_entropy(bin_conf_p,
targets_weighted,
reduction='sum')
# Compute max conf across batch for hard negative mining
# Confidence Loss Including Positive and Negative Examples
# the version 0922 that I use the neg samples from binary classification as the neg for multi-classification
'''
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
'''
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
#########################################################################
# used fake_pos or not
# Hard Negative Mining
#loss_c[fake_pos.view(-1, 1)] = 0 # filter out fake pos boxes for now
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
neg_multi = neg
'''
loss_c = loss_c.view(-1, 1)
loss_c[fake_pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
#neg_multi = neg
'''
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
#soft_label_val =smooth_label(targets_weighted, self.num_classes, eps=0.001)
#loss_c = crossentropy(conf_p, soft_label_val)
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# for dist loss
conf_t_new = conf_t.view(-1)
nonzero_index = torch.nonzero(conf_t_new)
conf_t_new = conf_t_new[nonzero_index]
conf_target_stand_dist = conf_target_stand_dist.view(
-1, self.num_classes)
pos_conf_target_stand_dist = conf_target_stand_dist[
nonzero_index].squeeze(1)
pos_dist = torch.gather(pos_conf_target_stand_dist,
dim=1,
index=conf_t_new)
neg_nonzero_index = torch.nonzero(neg.view(-1))
neg_conf_target_stand_dist = conf_target_stand_dist[
neg_nonzero_index].squeeze(1)
neg_dist = neg_conf_target_stand_dist[:, 0]
dist_loss = -pos_dist.sum() + 1 / 5 * neg_dist.sum()
# weight
'''
conf_p_t = conf_data[(pos_idx).gt(0)].view(-1, self.num_classes)
targets_weighted = conf_t[(pos).gt(0)]
loss_c = F.cross_entropy(conf_p_t, targets_weighted, reduction='sum')
conf_p_f = conf_data[(neg_idx).gt(0)].view(-1, self.num_classes)
targets_weighted = conf_t[(neg).gt(0)]
loss_c = loss_c + F.cross_entropy(conf_p_f, targets_weighted, reduction='sum') * 0.2
'''
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g) + \beta Lbinconf(x, c)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_bin /= N
dist_loss /= N
return loss_l, loss_c, loss_bin, dist_loss, pos, neg_binary, neg_multi
def forward(self, predictions, targets):
# 回归信息，置信度，先验框
loc_data, conf_data, priors = predictions
# 计算出batch_size
num = loc_data.size(0)
# 取出所有的先验框
priors = priors[:loc_data.size(1), :]
# 先验框的数量
num_priors = (priors.size(0))
num_classes = self.num_classes
# 创建一个tensor进行处理
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
# 获得框
truths = targets[idx][:, :-1].data
# 获得标签
labels = targets[idx][:, -1].data
# 获得先验框
defaults = priors.data
# 找到标签对应的先验框
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# 转化成Variable
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
# 所有conf_t>0的地方，代表内部包含物体
pos = conf_t > 0
# 求和得到每一个图片内部有多少正样本
num_pos = pos.sum(dim=1, keepdim=True)
# 计算回归loss
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# 转化形式
batch_conf = conf_data.view(-1, self.num_classes)
# 你可以把softmax函数看成一种接受任何数字并转换为概率分布的非线性方法
# 获得每个框预测到真实框的类的概率
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
loss_c = loss_c.view(num, -1)
loss_c[pos] = 0
# 获得每一张图新的softmax的结果
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
# 计算每一张图的正样本数量
num_pos = pos.long().sum(1, keepdim=True)
# 限制负样本数量
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# 计算正样本的loss和负样本的loss
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets, teacher_data):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_teacher, conf_teacher = teacher_data
loc_data, conf_data, landm_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data
labels = targets[idx][:, -1].data
landms = targets[idx][:, 4:14].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
landms, loc_t, conf_t, landm_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
zeros = torch.tensor(0).cuda()
# landm Loss (Smooth L1)
# Shape: [batch,num_priors,10]
pos1 = conf_t > zeros
num_pos_landm = pos1.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
landm_p = landm_data[pos_idx1].view(-1, 10)
landm_t = landm_t[pos_idx1].view(-1, 10)
loss_landm = F.smooth_l1_loss(landm_p, landm_t, reduction='sum')
pos = conf_t != zeros
conf_t[pos] = 1
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loc_t2 = loc_teacher[pos_idx].view(-1, 4)
loss_fn = torch.nn.MSELoss(reduction='sum')
loss1 = loss_fn(loc_p, loc_t)
loss2 = loss_fn(loc_t2, loc_t)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
if loss1 > loss2:
loss_l = loss_l + self.r_weight * loss1
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
m = nn.Softmax(dim=1)
loss_fn2 = nn.BCEWithLogitsLoss(reduction='sum')
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
conf_t2 = conf_teacher[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_soft = loss_fn2(m(conf_p), m(conf_t2))
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
loss_c = loss_c + self.c_weight * loss_soft
# import ipdb;
# ipdb.set_trace()
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_landm /= N1
return loss_l, loss_c, loss_landm
def forward(self, predictions, priors, targets, pass_index=None):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
pre_conf is used to use Early reject or not
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0)) if priors.dim() == 2 else priors.size(1)
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
if priors.dim() == 3:
defaults = priors.data[idx, :, :]
else:
defaults = priors.data
# if pass_index is not None:
# defaults = defaults[pass_index_data[idx].unsqueeze(1).expand_as(defaults)].view(-1, num)
# if defaults.shape[0] != 6375:
# print('ERROR')
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
if pass_index is not None:
pass_index_data = pass_index.data
loc_t = loc_t[pass_index_data.unsqueeze(2).expand_as(loc_t)].view(
-1, 4)
conf_t1 = conf_t[pass_index_data]
loc_data = loc_data[pass_index_data.unsqueeze(2).expand_as(
loc_data)].view(-1, 4)
print(conf_t1.shape[0] / num)
# conf_data1 = conf_data[pass_index_data.unsqueeze(2).expand_as(conf_data)].view(-1, self.num_classes)
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
if pass_index is not None:
conf_t1 = Variable(conf_t1, requires_grad=False)
pos = conf_t1 > 0
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
else:
pos = conf_t > 0
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
pos = conf_t > 0
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# ER
if pass_index is None:
x_max = batch_conf.data.max()
temp = torch.exp(batch_conf[:, 0] - x_max) / torch.sum(
torch.exp(batch_conf - x_max), 1)
# print(temp.data.max())
temp = temp < 0.99
temp_idx = temp.view(num, -1)
# Hard Negative Mining
loss_c[pos.view(-1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
if pass_index is not None:
loss_c[1 - pass_index_data] = 0
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
if pass_index is None:
index = (pos + temp_idx).gt(0)
else:
index = None
return loss_l, loss_c, index
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t,requires_grad=False)
pos = conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1,4)
loc_t = loc_t[pos_idx].view(-1,4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1,self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1,1))
# Hard Negative Mining
loss_c[pos.view(-1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_,loss_idx = loss_c.sort(1, descending=True)
_,idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1,keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data, loc_five_data = predictions
# print('loc_data shape:', loc_data.shape, '\n loc_five_data:', loc_five_data.shape)
priors = priors
num = loc_data.size(0) # batch size
num_priors = (
priors.size(0)
) # [21824, 4] total number of r anchor in one img if img.shape = (1024, 1024)
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(
num,
num_priors) # LongTensor , class label for priors box match the gt
loc_five = torch.Tensor(num, num_priors, 10) # for 5 location points
# print("before:", loc_t,conf_t,loc_five)
for idx in range(num):
# truths = targets[idx][:, :-1].data # bbox, x1, y1, x2, y2: 0-1
truths = targets[idx][:, :4].data # bbox, x1, y1, x2, y2: 0-1
truths_five = targets[idx][:, 5:].data # coords 10
labels = targets[idx][:, 4].data
defaults = priors.data
# match(self.threshold, truths, defaults, self.variance, labels, loc_t, conf_t, idx) # key important
match_(self.threshold, truths, truths_five, defaults,
self.variance, labels, loc_t, conf_t, loc_five,
idx) # key important
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
loc_five = loc_five.cuda()
# loc_t is changed when math done!!!!
# should loc_five change same time!!!!
pos = conf_t > 0 # only optimizer positive anchors?
print("pos conf_t:", conf_t.shape, pos.shape,
pos.sum()) # why all of pos is < 0????
# print("after:",loc_t,conf_t, loc_five)
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
# print("pos_idx shape before:", pos.unsqueeze(pos.dim()).shape)
pos_idx = pos.unsqueeze(pos.dim()).expand_as(
loc_data) # think more time
pos_idx_five = pos.unsqueeze(pos.dim()).expand_as(loc_five_data)
# print("pos_idx shape after:", pos_idx.shape)
loc_p = loc_data[pos_idx].view(-1,
4) # choose positive loc_p from pred
# print("loc_p:", loc_p) # is empty....
loc_t = loc_t[pos_idx].view(
-1, 4) # get correspond loc_t to loc_p which have matched
loc_five = loc_five[pos_idx_five].view(-1, 10)
loc_f = loc_five_data[pos_idx_five].view(-1, 10)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# print("loss_l:",loc_p, loc_t)
loss_coords = F.mse_loss(loc_five, loc_f, reduction='sum')
# print("loss_coords:",loc_five, loc_f, loss_coords)
# compute five key point loss :
# change the targets [4, 1, 10], predictions is three: loc_data, conf_data, loc_data_pair
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# print("sum of neg:", neg.sum(), '\n', "sum of pos:", pos.sum()) # may zero !!!!!!!!
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
# print("???????", conf_data.shape, '\n', conf_p, conf_p.shape)
# conf_p may empty!!!!!!!!!!
if conf_p.shape[0] == 0:
print(pos_idx.shape, neg_idx.shape, conf_p)
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# print("?XX"*3)
"""
try:
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
except:
print("wwwwwww", targets_weighted.max()) # may is -9223372036854775808 ???
"""
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + ¦ÁLloc(x,l,g) + betaLloc_f(x,l,g_f)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_coords /= N
return loss_l, loss_c, loss_coords
def forward(self, preds, targets):
loc_data, conf_data, priors = preds
bs = loc_data.size(0) # batch size
priors = priors[:loc_data.size(1), :]
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(bs, num_priors, 4)
conf_t = torch.LongTensor(bs, num_priors)
for idx in range(bs):
truths = targets[idx][:, :-1].data
label = targets[idx][:, -1].data
defaults = priors.data
match(self.threshold, truths, label, defaults, self.variance,
loc_t, conf_t, idx)
loc_t = loc_t.to(self.device)
conf_t = conf_t.to(self.device)
pos = conf_t > 0
num_pos = pos.sum(dim=1, keepdim=True)
# Localization Loss (Smooth L1)
# Shape: [batch, num_priors, 4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max conf across batch for hard negative mining
# if diff both classes is small, the loss_c will be large
batch_conf = conf_data.view(-1, num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c = loss_c.view(bs, -1)
loss_c[pos] = 0 # filter out pos boxes for now
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(
1) # idx is more small, loss is more large
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(-1, num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p,
targets_weighted,
weight=self.weight,
reduction='sum')
# sum of losses: L(x, c, l, g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, targets):
# 回归信息，置信度，先验框
loc_data, conf_data, priors = predictions
# loc_data torch.Size([4, 8732, 4])
# conf_data torch.Size([4, 8732, 3])
# priors torch.Size([8732, 4])
# 计算出batch_size
num = loc_data.size(0) # 4 batchsize
# 取出所有的先验框
priors = priors[:loc_data.size(1), :] # torch.Size([8732, 4])
# 先验框的数量
num_priors = (priors.size(0)) # 8732
# 创建一个tensor进行处理
loc_t = torch.Tensor(num, num_priors, 4) # torch.Size([4, 8732, 4])
conf_t = torch.LongTensor(num, num_priors) # torch.Size([4, 8732])
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
priors = priors.cuda()
for idx in range(num): # 这是batchsize的长度
# 获得框
truths = targets[idx][:, :-1] # 单个图片中所有物体的位置信息 torch.Size([1, 4])
# 获得标签
labels = targets[idx][:, -1] # 单个图片的所有物体的类别信息 torch.Size([1])
# 获得先验框
defaults = priors # torch.Size([8732, 4])
# 找到标签对应的先验框
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
# 转化成Variable
# 不清楚这两行代码作用,注释掉仍然能运行
loc_t = Variable(loc_t,
requires_grad=False) # torch.Size([4, 8732, 4])
conf_t = Variable(conf_t, requires_grad=False) # torch.Size([4, 8732])
# 所有conf_t>0的地方，代表内部包含物体
pos = conf_t > 0 # torch.Size([4, 8732])
# 求和得到每一个图片内部有多少正样本
num_pos = pos.sum(dim=1, keepdim=True) # torch.Size([4, 1])
# 计算回归loss
pos_idx = pos.unsqueeze(pos.dim()).expand_as(
loc_data) # torch.Size([4, 8732, 4])
loc_p = loc_data[pos_idx].view(-1,
4) # torch.Size([44, 4]) # 预测框的位置信息
loc_t = loc_t[pos_idx].view(-1,
4) # torch.Size([44, 4]) # 真值框的位置信息
# loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
loss_l = F.smooth_l1_loss(loc_p, loc_t,
reduction='sum') # 建议使用这行代码,上一行已废弃
# 转化形式
batch_conf = conf_data.view(-1,
self.num_classes) # torch.Size([34928, 3])
# 你可以把softmax函数看成一种接受任何数字并转换为概率分布的非线性方法
# 获得每个框预测到真实框的类的概率
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1)) # torch.Size([34928, 1])
loss_c = loss_c.view(num, -1) # torch.Size([4, 8732])
loss_c[pos] = 0
# 获得每一张图新的softmax的结果
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
# 计算每一张图的正样本数量
num_pos = pos.long().sum(1, keepdim=True) # torch.Size([4, 1])
# 限制负样本数量
num_neg = torch.clamp(self.negpos_ratio * num_pos,
max=pos.size(1) - 1) # torch.Size([4, 1])
neg = idx_rank < num_neg.expand_as(idx_rank) # torch.Size([4, 8732])
# 筛选出前self.negpos_ratio*num_pos个样本
# 计算正样本的loss和负样本的loss
pos_idx = pos.unsqueeze(2).expand_as(
conf_data) # torch.Size([4, 8732, 3])
neg_idx = neg.unsqueeze(2).expand_as(
conf_data) # torch.Size([4, 8732, 3])
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes) # torch.Size([176, 3])
targets_weighted = conf_t[(pos + neg).gt(0)] # torch.Size([176])
# loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False) # torch.Size([])
loss_c = F.cross_entropy(conf_p, targets_weighted,
reduction='sum') # 建议使用这行代码,上一行已废弃
# torch.Size([176, 3])
# torch.Size([176])
N = num_pos.data.sum() # tensor(44, device='cuda:0')
# N = num_pos.sum() # tensor(44, device='cuda:0')
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data = predictions # (batch_size,num_priors,4) / (batch_size,num_priors,num_classes)
priors = priors # (num_priors,4)
num = loc_data.size(0) # batch_size
num_priors = (priors.size(0)) # num_priors
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes,
#将batch_size内每张图像中pred bbox与gt bbox做匹配，进一步计算loss
loc_t = torch.Tensor(num, num_priors, 4) #gt_loc定义好
conf_t = torch.LongTensor(num, num_priors) #gt_conf定义好
for idx in range(num): # 在batch_size中遍历每张图
truths = targets[idx][:,:-1].data # 前4个参数是gt bbox
labels = targets[idx][:,-1].data # 最后1个参数是gt label
defaults = priors.data # 这个defaults定义很好，就是SSD中预定义的default box
# match函数在box_utils.py里,返回的是conf_t + loc_t，对应gt_cls，gt_offsets
match(self.threshold,truths,defaults,self.variance,labels,loc_t,conf_t,idx)
# match这个函数给每个ground truth匹配了最好的priors，给每个priors匹配最好的ground truth
# 经过encode后的offset([g_cxcy, g_wh])->loc_t,top class label for each prior->conf_t
if GPU:
loc_t = loc_t.cuda()#刚刚返回的gt的位置loc_t
conf_t = conf_t.cuda()#刚刚返回的gt的类别conf_t
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t,requires_grad=False)
pos = conf_t > 0 # 从gt里取出正样本，正样本才需要计算loc loss
# Localization Loss (Smooth L1)
# loc Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data) # 相当于取出所有正样本对应的index位置
loc_p = loc_data[pos_idx].view(-1,4) #取出预测结果里的正样本pred bbox，结合RFB_Net_vgg.py和detection.py，可以发现其实预测的也是offsets
# 也就是保留与计算出来的positive的default box所对应的卷积生成的encode offset（相当于预测的）
loc_t = loc_t[pos_idx].view(-1,4) # gt offsets也reshape
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False) # Localization Loss (Smooth L1)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1,self.num_classes) # batch_size内所有pred bbox进行reshape操作
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1,1)) #把conf_t变为和batch_conf相同shape，正负样本分类loss
# Hard Negative Mining，仅筛选难负样本计算loss
loss_c[pos.view(-1,1)] = 0 # filter out pos boxes for now，OHEM操作不考虑正样本，仅在负样本上操作
loss_c = loss_c.view(num, -1) # 按图像归类各个负样本
_,loss_idx = loss_c.sort(1, descending=True) # loss降序排序，那么仅需要选择前面的高loss即可
_,idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1,keepdim=True) # 正样本数量
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1) # 由正样本数量按1：3比例得出需保留的难负样本数量
neg = idx_rank < num_neg.expand_as(idx_rank) # 结合_,idx_rank = loss_idx.sort(1)理解，为了取出难neg pred bbox
# Confidence Loss Including Positive and Negative Examples最终只有难负样本loss + 正样本loss参与模型参数的更新
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes) # pred bbox的预测结果，经过难负样本挖掘后留存下来的
targets_weighted = conf_t[(pos+neg).gt(0)] # 剩余需要计算cls gt label，包含了正负样本的gt label
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False) # 分类的交叉熵损失函数
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1) # N: number of matched default boxes
loss_l/=N
loss_c/=N
return loss_l,loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data = predictions # loc_data shape: tensor.Size(64, 21824, 4)
# # conf_data shape: torch.Size([64, 21824, 2])
priors = priors # priors shape: torch.Size([21824, 4])
# priors: tensor([[0.x, 0.x, 0.x, 0.x], [0.x, 0.x, 0.x, 0.x], ...])
num = loc_data.size(0) # num: 64, this is batch size
num_priors = (priors.size(0)
) # num_priors: 21824, total number of anchors
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors,
4) # loc_t: torch.Size([64, 21824, 4])
conf_t = torch.LongTensor(
num, num_priors) # conf_t: torch.Size([64, 21824])
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = priors.data
# threshold: 0.35
# variance: [0.1, 0.2]
# idx : 0, 1, ...., or 63 which image
# loc_t: [64, 21824, 4]
# conf_t: [64, 21824, 2]
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# conf[best_truth_overlap < threshold] = 0
# dim = 21824, which is also the prior number
# conf_t: tensor([[0, 0, ....],
# [0, 0, 0, ....]
# ...])
# conf_t.shape: torch.Size([64, 21824])
# loc_t torch.Size([64, 21824, 4])
pos = conf_t > 0 # torch.Size(64, 21824)
# pos: tensor([[False, False, ...], num = 64
# [False, False, ...]]), # almost all false
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
""" here, loc_data = torch.Size([645, 21824, 4]) """
pos_idx = pos.unsqueeze(pos.dim()).expand_as(
loc_data) # torch.Size([64, 21824, 4])
# pos_idx: tensor([[[False, False, False, False]]])
loc_p = loc_data[pos_idx].view(-1, 4)
# loc_p: positive predicted sample (prior)s location, tensor([[1.074, -0.836, -0.934, 0.414]])
# loc_p.shape: torch.Size([1186, 4]), torch.Size([num of True, 4])
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
""" now we are dueling with classes """
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
# conf_data.shape: torch.Sie([64, 21824, 2])
# batch_conf.shape: torch.Size(64x21824=1396736, 2)
# batch_conf
# tensor([[0.0473, -0.1172], [0.1001, 0.2789], ...])
# conf_t.shape: torch.Size([64, 21824]),
# conf_t: almost all 0
#
# log_sum_exp: log(softmax(batch_conf))
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, targets):
# 回归信息，置信度，先验框
loc_data, conf_data, priors = predictions
# 计算出batch_size
num = loc_data.size(0)
# 取出所有的先验框
priors = priors[:loc_data.size(1), :]
# 先验框的数量
num_priors = (priors.size(0))
num_classes = self.num_classes
# 创建一个tensor进行处理
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
# 获得框
truths = targets[idx][:, :-1].data
# 获得标签
labels = targets[idx][:, -1].data
# 获得先验框
defaults = priors.data
# 找到标签对应的先验框 ！！！
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
# if self.use_gpu:
# loc_t = loc_t.cuda()
# conf_t = conf_t.cuda()
# 所有conf_t>0的地方，代表内部包含物体
pos = conf_t > 0
# 求和得到每一个图片内部有多少正样本
num_pos = pos.sum(dim=1, keepdim=True)
# 回归
# 计算回归loss，使用正样本的先验框进行计算，背景框无意义
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# 计算置信度loss，分类
# 转化形式
batch_conf = conf_data.view(-1, self.num_classes)
# 你可以把softmax函数看成一种接受任何数字并转换为概率分布的非线性方法
# 获得每个框预测到真实框的类的概率
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# 对预测结果分布进行修改 批量归一化
loss_c = loss_c.view(num, -1)
loss_c[pos] = 0
# 获得每一张图新的softmax的结果
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
# 计算每一张图的正样本数量
num_pos = pos.long().sum(1, keepdim=True)
# 限制负样本数量
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# 计算正样本的loss和负样本的loss
# 平衡正负样本1：3 8732个框 可能只有十几个正样本
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
# loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False) size_average (bool, optional) – 默认情况下，是mini-batchloss的平均值，然而，如果size_average=False，则是mini-batchloss的总和
loss_c = F.cross_entropy(conf_p, targets_weighted,
reduction='sum') #改版后使用sum
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
# predictions.shape == ([32, 16800, 4]), ([32, 16800, 2]), ([32, 16800, 10])
# priors.shape == [16800, 4]
# len(targets) == 32, targets[0].shape == [num_of_faces_in_this_image, 15], 15 = 4(bbox) + 5*2(lmk) + 1(have_lmk)
loc_data, conf_data, landm_data = predictions
priors = priors
num = loc_data.size(0) # 32 batch
num_priors = (priors.size(0)) # 16800 anchor
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data # bbox
labels = targets[idx][:, -1].data # have_landmark
landms = targets[idx][:, 4:14].data # everyone's lmk
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels, landms, loc_t, conf_t, landm_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
# print(loc_t.shape) # [32, 16800, 4]
# print(conf_t.shape) # [32, 16800]
# print(landm_t.shape) # [32, 16800, 10]
# exit()
# LANDMARK LOSS
zeros = torch.tensor(0).cuda()
# landm Loss (Smooth L1)
# Shape: [batch,num_priors,10]
pos1 = conf_t > zeros
num_pos_landm = pos1.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
landm_p = landm_data[pos_idx1].view(-1, 10)
# print(landm_p.shape) # [xxxx,10]
landm_t = landm_t[pos_idx1].view(-1, 10)
# print(landm_t.shape) # [xxxx,10]
loss_landm = F.smooth_l1_loss(landm_p, landm_t, reduction='sum')
# print(loss_landm) # xxxxx.xxxx
# LOCALIZATION LOSS
pos = conf_t != zeros
conf_t[pos] = 1
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# CLASSIFICATION LOSS
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_landm /= N1
return loss_l, loss_c, loss_landm
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
#[ batch_size,num_priors,4 ]
#[batch_size,num_priors,21]
#[batch_size,num_priors,2]
loc_data, conf_data, obj_data = predictions
priors = priors
#bath_size
num = loc_data.size(0)
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
obj_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
obj_t = conf_t.clone()
obj_t[conf_t > 0] = 1
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
obj_t = obj_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
obj_t = Variable(obj_t, requires_grad=False)
obj_conf_data = obj_data[:, :, 1].detach()
#print(obj_data.requires_grad)
#print(obj_conf_data.requires_grad)
pos = conf_t > 0
#print(type(pos))
neg_positive = obj_conf_data < self.obj_score
#print(type(neg_positive))
neg_positive = (pos + neg_positive) > 2
pos = pos - neg_positive
#print(pos.type())
#byte tensor
# for pose conf_t > 0 ---> 1
# for neg_positive conf < obj_score --> 1
# 1 1 -> 0 # focus
# 1 0 -> 1
# 0 1 -> 0
# 0 0 -> 0
#print(type(pos))
#pos = ( conf_t > 0 ) - (obj_conf_data <= self.obj_score)
#pos[ (obj_conf_data < self.obj_score).detach()] = 0
if pos.data.long().sum() == 0:
pos = conf_t > 0
#print('conf_t shape:'+str(conf_t.shape))
#print('conf_t >0 shape:'+str( (conf_t>0).sum()))
#print('obj_t > obj_score'+str( (obj_t > self.obj_score).sum() ))
#print('pos shape:'+str( pos.sum() ))
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
pos_obj = obj_t > 0
#print('pos_obj shape: '+str(pos_obj.shape))
batch_obj_conf = obj_data.view(-1, 2)
loss_obj = log_sum_exp(batch_obj_conf) - batch_obj_conf.gather(
1, obj_t.view(-1, 1))
loss_obj[pos_obj] = 0
loss_obj = loss_obj.view(num, -1)
_, loss_obj_idx = loss_obj.sort(1, descending=True)
_, idx_obj_rank = loss_obj_idx.sort(1)
num_obj_pos = pos_obj.long().sum(1, keepdim=True)
num_obj_neg = torch.clamp(self.negpos_ratio * num_obj_pos,
max=pos_obj.size(1) - 1)
#print('num_obj_pos:'+str(num_obj_pos.shape))
#print('num_obj_neg:'+str(num_obj_neg.shape))
neg_obj = idx_obj_rank < num_obj_neg.expand_as(idx_obj_rank)
pos_obj_idx = pos_obj.unsqueeze(2).expand_as(obj_data)
neg_obj_idx = neg_obj.unsqueeze(2).expand_as(obj_data)
conf_obj_p = obj_data[(pos_obj_idx + neg_obj_idx).gt(0)].view(-1, 2)
targets_weighted = obj_t[(pos_obj + neg_obj).gt(0)]
loss_obj = F.cross_entropy(conf_obj_p,
targets_weighted,
size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
#print('num_pos:'+str(num_pos.sum()))
#print('num_neg:'+str(num_neg.sum()))
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
#print('conf_p.shape'+str(conf_p.shape))
#print('targets_weighted'+str(targets_weighted.shape))
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum(), 1)
loss_l /= N * 1.0
loss_c /= N * 1.0
N1 = max(num_obj_neg.data.sum(), 1)
loss_obj /= N1
loss_obj = 0.4 * loss_obj
return loss_l, loss_c, loss_obj
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
bin_conf: torch.size(batch_size,num_priors,2)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data, bin_conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
bin_conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = priors.data
match_3_terms(self.threshold, truths, defaults, self.variance,
labels, loc_t, conf_t, bin_conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
bin_conf_t = bin_conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
bin_conf_t = Variable(bin_conf_t, requires_grad=False)
pos = bin_conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
#[0., 47., 54., 54., 48., 69., 45., 91., 41., 189., 51., 57., 51., 43., 48., 514., 80., 107., 68., 32., 65.]
loss_l_elements = F.smooth_l1_loss(loc_p, loc_t,
reduction='none').sum(1)
conf_t_label = conf_t[conf_t > 0]
conf_t_stat = torch.zeros(num_classes).cuda()
for index in range(1, num_classes):
conf_t_stat[index] = (conf_t_label == index).sum()
conf_t_weights = torch.zeros(num_classes).cuda()
for index in range(1, num_classes):
if conf_t_stat[index] > 0:
conf_t_weights[index] = 1. / conf_t_stat[index]
loss_l = 0
#conf_t_weights = torch.exp(1-torch.tensor([0., 10., 12., 12., 10., 15., 11., 17., 16., 34., 14., 19., 15., 12., 10., 66., 16., 10.,
# 17., 10., 15.])/66).cuda()
conf_t_weights = torch.exp(
torch.tensor([
2, 1.3930, 1.2377, 2.3323, 1.7176, 2.0606, 1.3950, 1.0631,
1.7324, 1.3473, 1.6245, 1.1843, 2.2063, 1.3083, 1.3608, 1.2330,
1.8409, 1.6459, 1.3869, 1.4504, 1.2606
])).cuda()
conf_t_weights = torch.ones(21).cuda()
for index in range(1, num_classes):
loss_l += conf_t_weights[index] * (
loss_l_elements[conf_t_label == index]).sum()
# Compute max binary_conf across batch for hard negative mining
batch_bin_conf = bin_conf_data.view(-1, 2)
loss_bin = log_sum_exp(batch_bin_conf) - batch_bin_conf.gather(
1, bin_conf_t.view(-1, 1))
# Hard Negative Mining
loss_bin[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_bin = loss_bin.view(num, -1)
_, loss_idx = loss_bin.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
neg_binary = neg
# Binary confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(bin_conf_data)
neg_idx = neg.unsqueeze(2).expand_as(bin_conf_data)
bin_conf_p = bin_conf_data[(pos_idx + neg_idx).gt(0)].view(-1, 2)
targets_weighted = bin_conf_t[(pos + neg).gt(0)]
loss_bin_elements = F.cross_entropy(bin_conf_p,
targets_weighted,
reduction='none')
conf_t_f_label_for_bin = conf_t[(pos + neg) > 0]
conf_t_f_stat_for_bin = torch.zeros(num_classes).cuda()
for index in range(0, num_classes):
conf_t_f_stat_for_bin[index] = (
conf_t_f_label_for_bin == index).sum()
conf_t_f_weights_for_bin = torch.zeros(num_classes).cuda()
for index in range(0, num_classes):
if conf_t_f_stat_for_bin[index] > 0:
conf_t_f_weights_for_bin[
index] = 1. / conf_t_f_stat_for_bin[index]
loss_b = 0
#conf_t_f_weights_for_bin = torch.exp(1 - torch.tensor(
# [0., 10., 12., 12., 10., 15., 11., 17., 16., 34., 14., 19., 15., 12., 10., 66., 16., 10.,
# 17., 10., 15.]) / 66).cuda()
conf_t_f_weights_for_bin = torch.exp(
torch.tensor([
2, 1.3930, 1.2377, 2.3323, 1.7176, 2.0606, 1.3950, 1.0631,
1.7324, 1.3473, 1.6245, 1.1843, 2.2063, 1.3083, 1.3608, 1.2330,
1.8409, 1.6459, 1.3869, 1.4504, 1.2606
])).cuda()
conf_t_f_weights_for_bin = torch.ones(21).cuda()
conf_t_f_weights_for_bin[0] *= 3
for index in range(0, num_classes):
loss_b += conf_t_f_weights_for_bin[index] * (
loss_bin_elements[conf_t_f_label_for_bin == index]).sum()
# Compute max binary_conf across batch for hard negative mining
batch_bin_conf = bin_conf_data.view(-1, 2)
batch_conf = conf_data.view(-1, self.num_classes - 1)
P_k = (batch_conf[:, ].t() + batch_bin_conf[:, 1]).t()
P_0 = batch_bin_conf[:, 0].unsqueeze(1) + torch.log(
torch.exp(batch_conf).sum(dim=1, keepdim=True))
P_logit = torch.cat((P_0, P_k), dim=1).view(num, -1, self.num_classes)
# Compute max conf across batch for hard negative mining
batch_P_logit = P_logit.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_P_logit) - batch_P_logit.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
neg_multi = neg
# Confidence Loss Including Positive and Negative Examples
'''
pos_idx = pos.unsqueeze(2).expand_as(P_logit)
neg_idx = neg.unsqueeze(2).expand_as(P_logit)
conf_p = P_logit[(pos_idx + neg_idx).gt(0)].view(-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_cls = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
'''
pos_idx = pos.unsqueeze(2).expand_as(P_logit)
conf_p = P_logit[(pos_idx).gt(0)].view(-1, self.num_classes)
targets_weighted = conf_t[(pos).gt(0)]
loss_mul_elements = F.cross_entropy(conf_p,
targets_weighted,
reduction='none')
conf_t_f_label_for_mul = conf_t[(pos) > 0]
conf_t_f_stat_for_mul = torch.zeros(num_classes).cuda()
for index in range(1, num_classes):
conf_t_f_stat_for_mul[index] = (
conf_t_f_label_for_mul == index).sum()
conf_t_f_weights_for_mul = torch.zeros(num_classes).cuda()
for index in range(1, num_classes):
if conf_t_f_stat_for_mul[index] > 0:
conf_t_f_weights_for_mul[
index] = 1. / conf_t_f_stat_for_mul[index]
loss_cls = 0
#conf_t_f_weights_for_mul = torch.exp(1 - torch.tensor(
# [0., 10., 12., 12., 10., 15., 11., 17., 16., 34., 14., 19., 15., 12., 10., 66., 16., 10.,
# 17., 10., 15.]) / 66).cuda()
conf_t_f_weights_for_mul = torch.exp(
torch.tensor([
2, 1.3930, 1.2377, 2.3323, 1.7176, 2.0606, 1.3950, 1.0631,
1.7324, 1.3473, 1.6245, 1.1843, 2.2063, 1.3083, 1.3608, 1.2330,
1.8409, 1.6459, 1.3869, 1.4504, 1.2606
])).cuda()
conf_t_f_weights_for_mul = torch.ones(21).cuda()
for index in range(1, num_classes):
loss_cls += conf_t_f_weights_for_mul[index] * (
loss_mul_elements[conf_t_f_label_for_mul == index]).sum()
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g) + \beta Lbinconf(x, c)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_cls /= N
loss_b /= N
return loss_l, loss_cls, loss_b, pos, neg_binary, neg_multi
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:,:-1].data
labels = targets[idx][:,-1].data
defaults = priors.data
match(self.threshold,truths,defaults,self.variance,labels,loc_t,conf_t,idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t,requires_grad=False)
pos = conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1,4)
loc_t = loc_t[pos_idx].view(-1,4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1,self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1,1))
# Hard Negative Mining
loss_c[pos.view(-1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_,loss_idx = loss_c.sort(1, descending=True)
_,idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1,keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = num_pos.data.sum()
loss_l/=N
loss_c/=N
return loss_l,loss_c
def forward(self,
predictions,
targets,
use_arm=False,
filter_object=False,
filter_score=0,
debug=False):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
# arm_loc_data, arm_conf_data, loc_data, conf_data, priors = predictions
if use_arm:
arm_loc_data, arm_conf_data, loc_data, conf_data, priors = predictions
else:
loc_data, conf_data, _, _, priors = predictions
num = loc_data.size(0)
priors = priors[:loc_data.size(1), :]
num_priors = (priors.size(0))
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
defaults = priors.data
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
if self.num_classes == 2:
labels = labels > 0
if use_arm:
bbox_weight = refine_match(self.threshold,
truths,
defaults,
self.variance,
labels,
loc_t,
conf_t,
idx,
arm_loc_data[idx].data,
use_weight=False)
else:
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
if use_arm and filter_object:
P = F.softmax(arm_conf_data, 2)
arm_conf_data_temp = P[:, :, 1]
object_score_index = arm_conf_data_temp <= self.object_score
pos = conf_t > 0
pos[object_score_index.detach()] = 0
else:
pos = conf_t > 0
num_pos = pos.sum(1, keepdim=True)
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
if debug:
if use_arm:
print("odm pos num: ", str(loc_t.size(0)), str(loc_t.size(1)))
else:
print("arm pos num", str(loc_t.size(0)), str(loc_t.size(1)))
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
N = num_pos.data.sum()
loss_l /= float(N)
loss_c /= float(N)
return loss_l, loss_c
def forward(self, predictions, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data, priors = predictions
num = loc_data.size(0)
priors = priors[:loc_data.size(1), :]
num_priors = (priors.size(0))
num_classes = self.num_classes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
if self.num_classes == 2:
labels = labels > 0
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
pos = conf_t > 0
num_pos = pos.sum(1, keepdim=True)
if self.OHEM:
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_hard = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_hard[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_hard = loss_hard.view(num, -1)
_, loss_idx = loss_hard.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
if num_pos.data.sum() > 0:
num_neg = torch.clamp(self.negpos_ratio * num_pos,
max=pos.size(1) - 1)
else:
fake_num_pos = torch.ones(32, 1).long() * 15
num_neg = torch.clamp(self.negpos_ratio * fake_num_pos,
max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p,
targets_weighted,
size_average=False)
else:
loss_c = F.cross_entropy(conf_p, conf_t, size_average=False)
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
if num_pos.data.sum() > 0:
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
N = num_pos.data.sum()
else:
loss_l = torch.zeros(1)
N = 1.0
loss_l /= float(N)
loss_c /= float(N)
return loss_l, loss_c
def forward(self, predictions, priors, targets):
#--------------------------------------------------------------------#
# 取出预测结果的三个值：框的回归信息，置信度，人脸关键点的回归信息
#--------------------------------------------------------------------#
loc_data, conf_data, landm_data = predictions
#--------------------------------------------------#
# 计算出batch_size和先验框的数量
#--------------------------------------------------#
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
#--------------------------------------------------#
# 创建一个tensor进行处理
#--------------------------------------------------#
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
# 获得真实框与标签
truths = targets[idx][:, :4].data
labels = targets[idx][:, -1].data
landms = targets[idx][:, 4:14].data
# 获得先验框
defaults = priors.data
#--------------------------------------------------#
# 利用真实框和先验框进行匹配。
# 如果真实框和先验框的重合度较高，则认为匹配上了。
# 该先验框用于负责检测出该真实框。
#--------------------------------------------------#
match(self.threshold, truths, defaults, self.variance, labels, landms, loc_t, conf_t, landm_t, idx)
#--------------------------------------------------#
# 转化成Variable
# loc_t (num, num_priors, 4)
# conf_t (num, num_priors)
# landm_t (num, num_priors, 10)
#--------------------------------------------------#
zeros = torch.tensor(0)
if self.cuda:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
zeros = zeros.cuda()
#------------------------------------------------------------------------#
# 有人脸关键点的人脸真实框的标签为1，没有人脸关键点的人脸真实框标签为-1
# 所以计算人脸关键点loss的时候pos1 = conf_t > zeros
# 计算人脸框的loss的时候pos = conf_t != zeros
#------------------------------------------------------------------------#
pos1 = conf_t > zeros
pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
landm_p = landm_data[pos_idx1].view(-1, 10)
landm_t = landm_t[pos_idx1].view(-1, 10)
loss_landm = F.smooth_l1_loss(landm_p, landm_t, reduction='sum')
pos = conf_t != zeros
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
#--------------------------------------------------#
# batch_conf (num * num_priors, 2)
# loss_c (num, num_priors)
#--------------------------------------------------#
conf_t[pos] = 1
batch_conf = conf_data.view(-1, self.num_classes)
# 这个地方是在寻找难分类的先验框
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# 难分类的先验框不把正样本考虑进去，只考虑难分类的负样本
loss_c[pos.view(-1, 1)] = 0
loss_c = loss_c.view(num, -1)
#--------------------------------------------------#
# loss_idx (num, num_priors)
# idx_rank (num, num_priors)
#--------------------------------------------------#
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
#--------------------------------------------------#
# 求和得到每一个图片内部有多少正样本
# num_pos (num, )
# neg (num, num_priors)
#--------------------------------------------------#
num_pos = pos.long().sum(1, keepdim=True)
# 限制负样本数量
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
#--------------------------------------------------#
# 求和得到每一个图片内部有多少正样本
# pos_idx (num, num_priors, num_classes)
# neg_idx (num, num_priors, num_classes)
#--------------------------------------------------#
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
# 选取出用于训练的正样本与负样本，计算loss
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
num_pos_landm = pos1.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
loss_landm /= N1
return loss_l, loss_c, loss_landm
def forward(self, predictions, priors, targets):
loc_data, conf_data, landm_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data
labels = targets[idx][:, -1].data
landms = targets[idx][:, 4:14].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels, landms, loc_t, conf_t, landm_t, idx)
zeros = torch.tensor(0)
if self.cuda:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
zeros = zeros.cuda()
# landm Loss (Smooth L1)
# Shape: [batch,num_priors,10]
pos1 = conf_t > zeros
num_pos_landm = pos1.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
landm_p = landm_data[pos_idx1].view(-1, 10)
landm_t = landm_t[pos_idx1].view(-1, 10)
loss_landm = F.smooth_l1_loss(landm_p, landm_t, reduction='sum')
pos = conf_t != zeros
conf_t[pos] = 1
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
targets_weighted = conf_t[(pos+neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_landm /= N1
return loss_l, loss_c, loss_landm
def forward(self, predictions, targets):
loc_data, conf_data, priors = predictions
# get batch_size
num = loc_data.size(0)
# get all default boxes
priors = priors[:loc_data.size(1), :]
num_priors = (priors.size(0))
num_classes = self.num_classes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
# get the box
truths = targets[idx][:, :-1].data
# get the label
labels = targets[idx][:, -1].data
# get the data
defaults = priors.data
# get the default box corresponding to the label
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if self.use_gpu:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# convert to Variable
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
# conf_t > 0
pos = conf_t > 0
# num of pos-samples around the box
num_pos = pos.sum(dim=1, keepdim=True)
# loss
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
batch_conf = conf_data.view(-1, self.num_classes)
# softmax
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
loss_c = loss_c.view(num, -1)
loss_c[pos] = 0
# softmax for each picture
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
# pos-samples num
num_pos = pos.long().sum(1, keepdim=True)
# constrain the num of nag-samples
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# pos-loss + nag-loss
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size, num_priors, num_classes) # n, 3(anchor), 3
loc shape: torch.size(batch_size,num_priors,4) # n, 3, 4 as we only count each anchor for only one cls not cal for every cls, for rcnn it does for every cls
priors shape: torch.size(num_priors, 4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size, num_objs, 5] (last idx is the label).
"""
loc_data, conf_data, landm_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
landm_t = torch.Tensor(num, num_priors, 10)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :4].data
labels = targets[
idx][:,
-1].data # label only has 1 and -1 and 2, 1 and 2 used for cls
landms = targets[idx][:, 4:14].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
landms, loc_t, conf_t, landm_t, idx)
if 1: # use gpu
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
landm_t = landm_t.cuda()
# cos label file including -1 landmarks so ignore this data for landmark regression
zeros = torch.tensor(0).cuda()
pos = conf_t > zeros
num_pos_landm = pos.long().sum(1, keepdim=True)
N1 = max(num_pos_landm.data.sum().float(), 1)
# 1. get index for face class
face_tensor = torch.tensor(1).cuda()
# Shape: [batch,num_priors,10]
face_pos = conf_t == face_tensor
face_pos_idx = face_pos.unsqueeze(face_pos.dim()).expand_as(
landm_data) # 32, 16800, 10
face_landm_p = landm_data[face_pos_idx].view(-1, 10)
face_landm_t = landm_t[face_pos_idx].view(-1, 10)
# 2. get index for mask class, set all these target landmarks to 0.
# conf_t is target and anchor, if anchor matched target bbox cls 1, then the conf_t is 1, if anchor matched cls2, conf_t is 2
# after match conf_t, we can get all cls2's anchors.
mask_tensor = torch.tensor(2).cuda()
mask_pos = conf_t == mask_tensor
mask_pos_idx = mask_pos.unsqueeze(mask_pos.dim()).expand_as(landm_data)
mask_landm_p = landm_data[mask_pos_idx].view(-1, 10)
mask_landm_t = landm_t[mask_pos_idx].view(-1, 10)
mask_landm_p[:, 4:] = 0
mask_landm_t[:, 4:] = 0
landm_p = torch.cat([face_landm_p, mask_landm_p], 0)
landm_t = torch.cat([face_landm_t, mask_landm_t], 0)
loss_landm = F.smooth_l1_loss(landm_p, landm_t)
##############################################################################################################
zeros = torch.tensor(0).cuda()
pos = conf_t != zeros
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t)
##############################################################################################################
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
# Note here, as label file including -1 label, so we have to make them to 0~2
no_landmark_pos = conf_t < zeros
conf_t[no_landmark_pos] = 1
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted)
##############################################################################################################
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
loss_landm /= N1
return loss_l, loss_c, loss_landm
def forward(self,
odm_data,
priors,
targets,
arm_data=None,
filter_object=False):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
arm_data (tuple): arm branch containg arm_loc and arm_conf
filter_object: whether filter out the prediction according to the arm conf score
"""
loc_data, conf_data = odm_data
if arm_data:
arm_loc, arm_conf = arm_data
priors = priors.data
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
#for object detection
if self.num_classes == 2:
labels = labels > 0
if arm_data:
refine_match(self.threshold, truths, priors, self.variance,
labels, loc_t, conf_t, idx, arm_loc[idx].data)
else:
match(self.threshold, truths, priors, self.variance, labels,
loc_t, conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
if arm_data and filter_object:
arm_conf_data = arm_conf.data[:, :, 1]
pos = conf_t > 0
object_score_index = arm_conf_data <= self.object_score
pos[object_score_index] = 0
else:
pos = conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, size_average=False)
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, size_average=False)
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = num_pos.data.sum()
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
#loc_data, conf_data, _ = predictions
loc_data, conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0))
# match priors (default boxes) and ground truth boxes
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data
labels = targets[idx][:, -1].data
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx)
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
pos = conf_t > 0
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4)
loc_t = loc_t[pos_idx].view(-1, 4)
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max conf across batch for hard negative mining
batch_conf = conf_data.view(-1, self.num_classes)
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1))
# Hard Negative Mining
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
loss_c = loss_c.view(num, -1)
_, loss_idx = loss_c.sort(1, descending=True)
_, idx_rank = loss_idx.sort(1)
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
neg = idx_rank < num_neg.expand_as(idx_rank)
# Confidence Loss Including Positive and Negative Examples
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
return loss_l, loss_c
def forward(self, predictions, priors, targets):
"""Multibox Loss
Args:
predictions (tuple): A tuple containing loc preds, conf preds,
and prior boxes from SSD net.
conf shape: torch.size(batch_size,num_priors,num_classes)
loc shape: torch.size(batch_size,num_priors,4)
priors shape: torch.size(num_priors,4)
ground_truth (tensor): Ground truth boxes and labels for a batch,
shape: [batch_size,num_objs,5] (last idx is the label).
"""
loc_data, conf_data = predictions
priors = priors
num = loc_data.size(0)
num_priors = (priors.size(0)
) #11620 all feature_maps grid default bboxes number
num_classes = self.num_classes
# match priors (default boxes) and ground truth boxes
"""
for循环中的代码是为了将输入的target改造成网络的学习目标,也就是计算损失时的target最终得到的是loc_t和conf_t
注:对于Tensor来说,在子函数中修改其值,原有的值也会跟着改变,因此match函数无返回值
"""
loc_t = torch.Tensor(num, num_priors, 4)
conf_t = torch.LongTensor(num, num_priors)
for idx in range(num):
truths = targets[idx][:, :-1].data # 真实loc
labels = targets[idx][:, -1].data # 真实label
defaults = priors.data
match(self.threshold, truths, defaults, self.variance, labels,
loc_t, conf_t, idx) # gt 和 default boxes
if GPU:
loc_t = loc_t.cuda()
conf_t = conf_t.cuda()
# wrap targets
loc_t = Variable(loc_t, requires_grad=False)
conf_t = Variable(conf_t, requires_grad=False)
"""
conf_t > 0等价于torch.gt(conf_t,0)或者conf_t.gt(0)
返回和conf_t同形状的Tensor,符合条件的为1,否则为0
"""
pos = conf_t > 0 #忽略背景,pos是mask
# Localization Loss (Smooth L1)
# Shape: [batch,num_priors,4]
pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
loc_p = loc_data[pos_idx].view(-1, 4) # predictions
loc_t = loc_t[pos_idx].view(-1, 4) # encoded offsets to learn
loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
# Compute max conf across batch for hard negative mining
"""
conf_data Shape:[batch,num_priors,num_classes]
batch_conf Shape:[batch*num_priors,num_classes]
因为pytorch中cross_entropy的input要求为[N,C]的2-d Tensor
"""
batch_conf = conf_data.view(-1, self.num_classes) #predictions
"""
conf_t的shape为[batch,num_priors],其中选中的正样本为相应的类别，未选中的为0
Tensor.gather(dim,index)在dim维度上，按照index = 1 。此处就是计算cross_entropy的x[class]项
loss(x,class) = −x[class]+log(∑jexp(x[j]))
"""
loss_c = log_sum_exp(batch_conf) - batch_conf.gather(
1, conf_t.view(-1, 1)) #为了筛选负样本
# Hard Negative Mining
"""
先将正样本loss置为0，然后对loss排序(每张图片内部挑选)之后，取前self.negpos_ratio*num_pos个负样本的loss
"""
loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes,为了选择负样本。
"""
下一步loss_c shape转变为[batch,num_priors]
下面这种挑选前n个数的操作
"""
loss_c = loss_c.view(num, -1)
a_, loss_idx = loss_c.sort(1, descending=True)
# print('loss_idx : ',loss_idx)
# print('loss_idx : ',loss_idx.size(),a_.size())
# print('a_ : ',a_)
b_, idx_rank = loss_idx.sort(1)
# print('idx_rank : ',idx_rank)
# print('b_ : ',b_)
# print('loss_idx : ',idx_rank.size(),b_.size())
num_pos = pos.long().sum(1, keepdim=True)
num_neg = torch.clamp(self.negpos_ratio * num_pos,
max=pos.size(1) - 1) # 夹紧范围，限制 num_neg的范围
neg = idx_rank < num_neg.expand_as(idx_rank) # 负样本 index 掩码
# print(neg.size(),' neg',neg)
# print('neg sum : ',neg.sum())
# print('num_pos : ',num_pos.sum(),'\n',num_pos)
# Confidence Loss Including Positive and Negative Examples
"""
上面几步的操作就是为获得pos_idx和neg_idx
conf_data 的shape为[batch,num_priors,num_classes]
"""
pos_idx = pos.unsqueeze(2).expand_as(conf_data)
neg_idx = neg.unsqueeze(2).expand_as(conf_data)
"""
(pos_idx+neg_idx).gt(0)的原因个人猜测可能是因为挑选的正样本和负样本可能会重复，因此将大于1的数变成1.
"""
# gt举例：torch.gt(x,1)# tensor 大于 1
conf_p = conf_data[(pos_idx + neg_idx).gt(0)].view(
-1, self.num_classes)
targets_weighted = conf_t[(pos + neg).gt(0)]
loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
# Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
N = max(num_pos.data.sum().float(), 1)
loss_l /= N
loss_c /= N
return loss_l, loss_c