246 lines
13 KiB
Python
246 lines
13 KiB
Python
|
# Loss functions
|
|||
|
|
|
|||
|
|
import torch
|
|||
|
|
import torch.nn as nn
|
|||
|
|
|
|||
|
|
from utils.metrics import bbox_iou
|
|||
|
|
from utils.torch_utils import is_parallel
|
|||
|
|
|
|||
|
|
|
|||
|
|
def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
|
|||
|
|
# return positive, negative label smoothing BCE targets 标签平滑，https://wenku.baidu.com/view/27fdf1deadf8941ea76e58fafab069dc51224773.html
|
|||
|
|
#机器学习样本中少量错误标签，影响预测效果，训练时假设可能存在错误，避免过分相信。如果是交叉熵，可以简单实现，成为标签平滑。
|
|||
|
|
return 1.0 - 0.5 * eps, 0.5 * eps
|
|||
|
|
|
|||
|
|
|
|||
|
|
class BCEBlurWithLogitsLoss(nn.Module):
|
|||
|
|
# BCEwithLogitLoss() with reduced missing label effects.
|
|||
|
|
#BCEWithLogitsLoss这个loss类将sigmoid操作和BCELoss（二进制交叉熵损失）集合到了一个类
|
|||
|
|
def __init__(self, alpha=0.05):
|
|||
|
|
super(BCEBlurWithLogitsLoss, self).__init__()
|
|||
|
|
self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss()
|
|||
|
|
self.alpha = alpha
|
|||
|
|
|
|||
|
|
def forward(self, pred, true):
|
|||
|
|
loss = self.loss_fcn(pred, true)
|
|||
|
|
pred = torch.sigmoid(pred) # prob from logits
|
|||
|
|
dx = pred - true # reduce only missing label effects
|
|||
|
|
# dx = (pred - true).abs() # reduce missing label and false label effects
|
|||
|
|
alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
|
|||
|
|
loss *= alpha_factor #loss乘以alpha_factor这个系数， 考虑到图片中有目标但是没有做标签的情况，false negative
|
|||
|
|
return loss.mean()
|
|||
|
|
|
|||
|
|
|
|||
|
|
class FocalLoss(nn.Module):
|
|||
|
|
# Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
|
|||
|
|
#FocalLoss主要是为了解决one-stage的目标检测中正负样本比例严重失衡的问题，损失函数降低了大量简单负样本在训练过程中的比例
|
|||
|
|
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
|
|||
|
|
super(FocalLoss, self).__init__()
|
|||
|
|
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
|
|||
|
|
self.gamma = gamma
|
|||
|
|
self.alpha = alpha
|
|||
|
|
self.reduction = loss_fcn.reduction
|
|||
|
|
self.loss_fcn.reduction = 'none' # required to apply FL to each element
|
|||
|
|
|
|||
|
|
def forward(self, pred, true):
|
|||
|
|
loss = self.loss_fcn(pred, true)
|
|||
|
|
# p_t = torch.exp(-loss)
|
|||
|
|
# loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability
|
|||
|
|
|
|||
|
|
# TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
|
|||
|
|
pred_prob = torch.sigmoid(pred) # prob from logits
|
|||
|
|
p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
|
|||
|
|
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
|
|||
|
|
modulating_factor = (1.0 - p_t) ** self.gamma
|
|||
|
|
loss *= alpha_factor * modulating_factor
|
|||
|
|
|
|||
|
|
if self.reduction == 'mean':
|
|||
|
|
return loss.mean()
|
|||
|
|
elif self.reduction == 'sum':
|
|||
|
|
return loss.sum()
|
|||
|
|
else: # 'none'
|
|||
|
|
return loss
|
|||
|
|
|
|||
|
|
|
|||
|
|
class QFocalLoss(nn.Module):
|
|||
|
|
# Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
|
|||
|
|
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
|
|||
|
|
super(QFocalLoss, self).__init__()
|
|||
|
|
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
|
|||
|
|
self.gamma = gamma
|
|||
|
|
self.alpha = alpha
|
|||
|
|
self.reduction = loss_fcn.reduction
|
|||
|
|
self.loss_fcn.reduction = 'none' # required to apply FL to each element
|
|||
|
|
|
|||
|
|
def forward(self, pred, true):
|
|||
|
|
loss = self.loss_fcn(pred, true)
|
|||
|
|
|
|||
|
|
pred_prob = torch.sigmoid(pred) # prob from logits
|
|||
|
|
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
|
|||
|
|
modulating_factor = torch.abs(true - pred_prob) ** self.gamma
|
|||
|
|
loss *= alpha_factor * modulating_factor
|
|||
|
|
|
|||
|
|
if self.reduction == 'mean':
|
|||
|
|
return loss.mean()
|
|||
|
|
elif self.reduction == 'sum':
|
|||
|
|
return loss.sum()
|
|||
|
|
else: # 'none'
|
|||
|
|
return loss
|
|||
|
|
|
|||
|
|
|
|||
|
|
#计算损失=（分类损失+置信度损失+框坐标回归损失）
|
|||
|
|
class ComputeLoss:
|
|||
|
|
# Compute losses
|
|||
|
|
def __init__(self, model, autobalance=False):
|
|||
|
|
super(ComputeLoss, self).__init__()
|
|||
|
|
self.sort_obj_iou = False
|
|||
|
|
device = next(model.parameters()).device # get model device
|
|||
|
|
h = model.hyp # hyperparameters 获得超参数！！！
|
|||
|
|
|
|||
|
|
# Define criteria 定义类别及目标性得分损失函数
|
|||
|
|
BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) #将'cls_pw'这两个参数传进来，在hyp.scratch.yaml里
|
|||
|
|
BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) #将'obj_pw'这两个参数传进来，在hyp.scratch.yaml里
|
|||
|
|
|
|||
|
|
# 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
|
|||
|
|
#这里g>0才考虑focal loss
|
|||
|
|
if g > 0:
|
|||
|
|
BCEcls, BCEobj = QFocalLoss(BCEcls, g), QFocalLoss(BCEobj, g)
|
|||
|
|
|
|||
|
|
det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module
|
|||
|
|
#设置3个特征图对应的损失函数的损失系数 80x80、40x40、20x20有相应的系数 显然80特征图系数最大
|
|||
|
|
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':
|
|||
|
|
setattr(self, k, getattr(det, k))
|
|||
|
|
|
|||
|
|
def __call__(self, p, targets): # predictions, targets, model __call__可以实例化对象名后直接调用这个函数，格式是：实例化对象名（参数）
|
|||
|
|
#p是网络的输出，targets是这个batch中所有图片标注的目标框信息
|
|||
|
|
#获取设备，用的是cuda
|
|||
|
|
device = targets.device
|
|||
|
|
#初始化各部分损失
|
|||
|
|
#类别损失、box回归损失、目标性得分损失（即置信度）
|
|||
|
|
lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
|
|||
|
|
#获得标签分类信息、边框信息（不同尺度上的预测框）、索引信息、anchors
|
|||
|
|
tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets
|
|||
|
|
|
|||
|
|
# Losses
|
|||
|
|
#遍历每一个预测输出
|
|||
|
|
for i, pi in enumerate(p): # layer index, layer predictions 在每一层特征图上迭代，比如先80x80，再40x40，最后20x20
|
|||
|
|
#根据indices获取索引，方便找到对应网格的输出
|
|||
|
|
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
|
|||
|
|
tobj = torch.zeros_like(pi[..., 0], device=device) # target obj tobj初始化为0
|
|||
|
|
|
|||
|
|
n = b.shape[0] # number of targets
|
|||
|
|
if n:
|
|||
|
|
#找到对应网格的输出，取出对应位置的预测值。若pi里为80x80，则那个维度数据对应此特征图上，下面pxy和pwh进行框微调，有专门公式
|
|||
|
|
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
|
|||
|
|
|
|||
|
|
# Regression
|
|||
|
|
#对输出的xywh做反算
|
|||
|
|
#想计算预测框的xy，这里是微调？
|
|||
|
|
pxy = ps[:, :2].sigmoid() * 2. - 0.5
|
|||
|
|
#想计算预测框的wh，这里是微调？ 通过偏移值，求出这个框真正的xywh
|
|||
|
|
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
|
|||
|
|
pbox = torch.cat((pxy, pwh), 1) # predicted box
|
|||
|
|
#计算边框损失，注意这个CIoU=True，计算的是是CIoU，bbox_iou可以选择传参呢！。 注意：tbox[i]里面是groundtruth
|
|||
|
|
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
|
|||
|
|
lbox += (1.0 - iou).mean() # iou loss 损失函数在这里了，通过iou算出iou的loss。求了mean，就变成一个均值。
|
|||
|
|
|
|||
|
|
# Objectness
|
|||
|
|
score_iou = iou.detach().clamp(0).type(tobj.dtype)
|
|||
|
|
if self.sort_obj_iou:
|
|||
|
|
sort_id = torch.argsort(score_iou)
|
|||
|
|
b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id]
|
|||
|
|
#根据model.gr设置objectness的标签值，有目标的conf分支权重。
|
|||
|
|
#不同anchor和gt bbox匹配度不一样，预测框和gt bbox的匹配度也不一样，如果权重设置一样肯定不是最优的
|
|||
|
|
#故将预测框和bbox的iou作为权重乘到conf分支，用于表征预测质量
|
|||
|
|
tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio
|
|||
|
|
|
|||
|
|
# Classification
|
|||
|
|
#如果类别数>1，才计算分类损失（即多类别损失）
|
|||
|
|
if self.nc > 1: # cls loss (only if multiple classes)
|
|||
|
|
t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets
|
|||
|
|
t[range(n), tcls[i]] = self.cp
|
|||
|
|
lcls += self.BCEcls(ps[:, 5:], t) # BCE对每个类别单独计算loss
|
|||
|
|
|
|||
|
|
# 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)]
|
|||
|
|
|
|||
|
|
#计算objectness的损失
|
|||
|
|
obji = self.BCEobj(pi[..., 4], tobj)
|
|||
|
|
lobj += obji * self.balance[i] # obj loss 考虑了balance的值，即不同的特征图大小考虑不同的权重！！！
|
|||
|
|
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'] #求最后总的损失时，还进行了加权
|
|||
|
|
lobj *= self.hyp['obj'] #超参里面有设置
|
|||
|
|
lcls *= self.hyp['cls'] #超参里面有设置
|
|||
|
|
bs = tobj.shape[0] # batch size
|
|||
|
|
|
|||
|
|
#总的loss=lbox + lobj + lcls，再乘以batchsize，返回
|
|||
|
|
return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()
|
|||
|
|
|
|||
|
|
def build_targets(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
|
|||
|
|
tcls, tbox, indices, anch = [], [], [], []
|
|||
|
|
gain = torch.ones(7, device=targets.device) # 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
|
|||
|
|
tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
|
|||
|
|
anch.append(anchors[a]) # anchors
|
|||
|
|
tcls.append(c) # class
|
|||
|
|
|
|||
|
|
return tcls, tbox, indices, anch
|