标签分配（label assignment）
什么是标签分配
标签分配（Label Assignment）标签分配策略是对训练过程中各个Anchor划分正负属性，并分配各自学习目标的策略方法，在整体上通过标签是否是非负即正可以分为硬标签分配和软标签分配。其中，硬标签分配可以分成静态分配策略和动态分配策略两类。
动态
- 静态分配策略
静态标签分配方法主要基于距离、IOU等先验知识设置固定阈值去区分正负样本，如FCOS、两阶段标检测算法、RFLA等。 - 动态分配策略
动态标签分配方法则根据不同策略动态设置阈值选择正负样本，如ATSS、PAA、OTA、DSL、SimOTA等。
OTA损失函数介绍
OTA（Optimal Transport Assignment for Object Detection）出处为2021年 CVPR会议上的一篇论文。该论文的贡献主要有以下两点：
- 提出了一种基于优化策略的标签分配方式，将 gt 看做 label 供应商，anchor 看做 label 需求方。对于正样本，将分类和回归的 loss 加权和作为传输花费，对于负样本，传输花费就为分类 loss，通过最小化该花费，让网络自己学习最优的标签分配方式。
- 免去了手工选定参数的方式来实现标签分配，让网络自己选择每个 gt 对应的 anchor 数量，而非提前设定，也能够较好的解决模棱两可的 anchor 分配问题，提高网络对这部分 anchor 的处理效果
论文：Optimal Transport Assignment for Object Detection
代码：OTA代码
背景
Label assignment 在object detection领域中发挥着非常重要的作用，它能够分配每个 anchor 的正负。但是传统的方法具有一些缺点，具体体现为：不同大小、形状、遮挡程度的目标，其 positive/negative 的判定条件应该是不同的。针对这个缺点，就有一些方法使用了动态分配的策略来实现label assignment。文章来源：https://www.toymoban.com/news/detail-649180.html
方法
这个方法可以看这个博客，讲的比较详细：博客文章来源地址https://www.toymoban.com/news/detail-649180.html
如何在yolo v5目标检测算法中改为OTA损失
步骤一、修改loss.py文件
import torch.nn.functional as F
from utils.metrics import box_iou
from utils.torch_utils import de_parallel
from utils.general import xywh2xyxy
class ComputeLossOTA:
# Compute losses
def __init__(self, model, autobalance=False):
super(ComputeLossOTA, self).__init__()
device = next(model.parameters()).device # get model device
h = model.hyp # hyperparameters
# Define criteria
BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
# Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets
# Focal loss
g = h['fl_gamma'] # focal loss gamma
if g > 0:
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
det = de_parallel(model).model[-1] # Detect() module
self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02]) # P3-P7
self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index
self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
for k in 'na', 'nc', 'nl', 'anchors', 'stride':
setattr(self, k, getattr(det, k))
def __call__(self, p, targets, imgs): # predictions, targets, model
device = targets.device
lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
bs, as_, gjs, gis, targets, anchors = self.build_targets(p, targets, imgs)
pre_gen_gains = [torch.tensor(pp.shape, device=device)[[3, 2, 3, 2]] for pp in p]
# Losses
for i, pi in enumerate(p): # layer index, layer predictions
b, a, gj, gi = bs[i], as_[i], gjs[i], gis[i] # image, anchor, gridy, gridx
tobj = torch.zeros_like(pi[..., 0], device=device) # target obj
n = b.shape[0] # number of targets
if n:
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
# Regression
grid = torch.stack([gi, gj], dim=1)
pxy = ps[:, :2].sigmoid() * 2. - 0.5
#pxy = ps[:, :2].sigmoid() * 3. - 1.
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
pbox = torch.cat((pxy, pwh), 1) # predicted box
selected_tbox = targets[i][:, 2:6] * pre_gen_gains[i]
selected_tbox[:, :2] -= grid
iou = bbox_iou(pbox, selected_tbox, CIoU=True) # iou(prediction, target)
if type(iou) is tuple:
lbox += (iou[1].detach() * (1 - iou[0])).mean()
iou = iou[0]
else:
lbox += (1.0 - iou).mean() # iou loss
# Objectness
tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * iou.detach().clamp(0).type(tobj.dtype) # iou ratio
# Classification
selected_tcls = targets[i][:, 1].long()
if self.nc > 1: # cls loss (only if multiple classes)
t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets
t[range(n), selected_tcls] = self.cp
lcls += self.BCEcls(ps[:, 5:], t) # BCE
# Append targets to text file
# with open('targets.txt', 'a') as file:
# [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
obji = self.BCEobj(pi[..., 4], tobj)
lobj += obji * self.balance[i] # obj loss
if self.autobalance:
self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
if self.autobalance:
self.balance = [x / self.balance[self.ssi] for x in self.balance]
lbox *= self.hyp['box']
lobj *= self.hyp['obj']
lcls *= self.hyp['cls']
bs = tobj.shape[0] # batch size
loss = lbox + lobj + lcls
return loss * bs, torch.cat((lbox, lobj, lcls)).detach()
def build_targets(self, p, targets, imgs):
indices, anch = self.find_3_positive(p, targets)
device = torch.device(targets.device)
matching_bs = [[] for pp in p]
matching_as = [[] for pp in p]
matching_gjs = [[] for pp in p]
matching_gis = [[] for pp in p]
matching_targets = [[] for pp in p]
matching_anchs = [[] for pp in p]
nl = len(p)
for batch_idx in range(p[0].shape[0]):
b_idx = targets[:, 0]==batch_idx
this_target = targets[b_idx]
if this_target.shape[0] == 0:
continue
txywh = this_target[:, 2:6] * imgs[batch_idx].shape[1]
txyxy = xywh2xyxy(txywh)
pxyxys = []
p_cls = []
p_obj = []
from_which_layer = []
all_b = []
all_a = []
all_gj = []
all_gi = []
all_anch = []
for i, pi in enumerate(p):
b, a, gj, gi = indices[i]
idx = (b == batch_idx)
b, a, gj, gi = b[idx], a[idx], gj[idx], gi[idx]
all_b.append(b)
all_a.append(a)
all_gj.append(gj)
all_gi.append(gi)
all_anch.append(anch[i][idx])
from_which_layer.append((torch.ones(size=(len(b),)) * i).to(device))
fg_pred = pi[b, a, gj, gi]
p_obj.append(fg_pred[:, 4:5])
p_cls.append(fg_pred[:, 5:])
grid = torch.stack([gi, gj], dim=1)
pxy = (fg_pred[:, :2].sigmoid() * 2. - 0.5 + grid) * self.stride[i] #/ 8.
#pxy = (fg_pred[:, :2].sigmoid() * 3. - 1. + grid) * self.stride[i]
pwh = (fg_pred[:, 2:4].sigmoid() * 2) ** 2 * anch[i][idx] * self.stride[i] #/ 8.
pxywh = torch.cat([pxy, pwh], dim=-1)
pxyxy = xywh2xyxy(pxywh)
pxyxys.append(pxyxy)
pxyxys = torch.cat(pxyxys, dim=0)
if pxyxys.shape[0] == 0:
continue
p_obj = torch.cat(p_obj, dim=0)
p_cls = torch.cat(p_cls, dim=0)
from_which_layer = torch.cat(from_which_layer, dim=0)
all_b = torch.cat(all_b, dim=0)
all_a = torch.cat(all_a, dim=0)
all_gj = torch.cat(all_gj, dim=0)
all_gi = torch.cat(all_gi, dim=0)
all_anch = torch.cat(all_anch, dim=0)
pair_wise_iou = box_iou(txyxy, pxyxys)
pair_wise_iou_loss = -torch.log(pair_wise_iou + 1e-8)
top_k, _ = torch.topk(pair_wise_iou, min(10, pair_wise_iou.shape[1]), dim=1)
dynamic_ks = torch.clamp(top_k.sum(1).int(), min=1)
gt_cls_per_image = (
F.one_hot(this_target[:, 1].to(torch.int64), self.nc)
.float()
.unsqueeze(1)
.repeat(1, pxyxys.shape[0], 1)
)
num_gt = this_target.shape[0]
cls_preds_ = (
p_cls.float().unsqueeze(0).repeat(num_gt, 1, 1).sigmoid_()
* p_obj.unsqueeze(0).repeat(num_gt, 1, 1).sigmoid_()
)
y = cls_preds_.sqrt_()
pair_wise_cls_loss = F.binary_cross_entropy_with_logits(
torch.log(y/(1-y)) , gt_cls_per_image, reduction="none"
).sum(-1)
del cls_preds_
cost = (
pair_wise_cls_loss
+ 3.0 * pair_wise_iou_loss
)
matching_matrix = torch.zeros_like(cost, device=device)
for gt_idx in range(num_gt):
_, pos_idx = torch.topk(
cost[gt_idx], k=dynamic_ks[gt_idx].item(), largest=False
)
matching_matrix[gt_idx][pos_idx] = 1.0
del top_k, dynamic_ks
anchor_matching_gt = matching_matrix.sum(0)
if (anchor_matching_gt > 1).sum() > 0:
_, cost_argmin = torch.min(cost[:, anchor_matching_gt > 1], dim=0)
matching_matrix[:, anchor_matching_gt > 1] *= 0.0
matching_matrix[cost_argmin, anchor_matching_gt > 1] = 1.0
fg_mask_inboxes = (matching_matrix.sum(0) > 0.0).to(device)
matched_gt_inds = matching_matrix[:, fg_mask_inboxes].argmax(0)
from_which_layer = from_which_layer[fg_mask_inboxes]
all_b = all_b[fg_mask_inboxes]
all_a = all_a[fg_mask_inboxes]
all_gj = all_gj[fg_mask_inboxes]
all_gi = all_gi[fg_mask_inboxes]
all_anch = all_anch[fg_mask_inboxes]
this_target = this_target[matched_gt_inds]
for i in range(nl):
layer_idx = from_which_layer == i
matching_bs[i].append(all_b[layer_idx])
matching_as[i].append(all_a[layer_idx])
matching_gjs[i].append(all_gj[layer_idx])
matching_gis[i].append(all_gi[layer_idx])
matching_targets[i].append(this_target[layer_idx])
matching_anchs[i].append(all_anch[layer_idx])
for i in range(nl):
if matching_targets[i] != []:
matching_bs[i] = torch.cat(matching_bs[i], dim=0)
matching_as[i] = torch.cat(matching_as[i], dim=0)
matching_gjs[i] = torch.cat(matching_gjs[i], dim=0)
matching_gis[i] = torch.cat(matching_gis[i], dim=0)
matching_targets[i] = torch.cat(matching_targets[i], dim=0)
matching_anchs[i] = torch.cat(matching_anchs[i], dim=0)
else:
matching_bs[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_as[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_gjs[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_gis[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_targets[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
matching_anchs[i] = torch.tensor([], device='cuda:0', dtype=torch.int64)
return matching_bs, matching_as, matching_gjs, matching_gis, matching_targets, matching_anchs
def find_3_positive(self, p, targets):
# Build targets for compute_loss(), input targets(image,class,x,y,w,h)
na, nt = self.na, targets.shape[0] # number of anchors, targets
indices, anch = [], []
gain = torch.ones(7, device=targets.device).long() # normalized to gridspace gain
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
g = 0.5 # bias
off = torch.tensor([[0, 0],
[1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m
# [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
], device=targets.device).float() * g # offsets
for i in range(self.nl):
anchors = self.anchors[i]
gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
# Match targets to anchors
t = targets * gain
if nt:
# Matches
r = t[:, :, 4:6] / anchors[:, None] # wh ratio
j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t'] # compare
# j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
t = t[j] # filter
# Offsets
gxy = t[:, 2:4] # grid xy
gxi = gain[[2, 3]] - gxy # inverse
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
l, m = ((gxi % 1. < g) & (gxi > 1.)).T
j = torch.stack((torch.ones_like(j), j, k, l, m))
t = t.repeat((5, 1, 1))[j]
offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
else:
t = targets[0]
offsets = 0
# Define
b, c = t[:, :2].long().T # image, class
gxy = t[:, 2:4] # grid xy
gwh = t[:, 4:6] # grid wh
gij = (gxy - offsets).long()
gi, gj = gij.T # grid xy indices
# Append
a = t[:, 6].long() # anchor indices
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
anch.append(anchors[a]) # anchors
return indices, anch
步骤二、在train.py和val.py中修改conpute_loss
- from utils.loss import ComputeLoss 改为ComputeLossOTA。
- 将 compute_loss = ComputeLoss(model) 中的ComputeLoss方法改为 ComputeLossOTA。
- loss, loss_items = compute_loss(pred, targets.to(device)) 括号内添加imgs。
- 在val.py中做出和如上所示的修改。
- 运行train.py即可进行训练过程。
到了这里，关于目标检测改进系列1：yolo v5网络中OTA损失函数替换的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！
