def build_targets(p, targets, model):
"""
:param p:torch.Size([2, 3, 19, 19, 85])*3
:param targets: [目标数,6]
:param model:
:return:
"""
# Build targets for compute_loss(), input targets(image,class,x,y,w,h)
det = model.module.model[-1] if type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel) \
else model.model[-1] # Detect() module = model.model[-1]
na, nt = det.na, targets.shape[0] # number of anchors=3, targets
tcls, tbox, indices, anch = [], [], [], []
gain = torch.ones(6, device=targets.device) # normalized to gridspace gain
off = torch.tensor([[1, 0], [0, 1], [-1, 0], [0, -1]], device=targets.device).float() # overlap offsets
at = torch.arange(na).view(na, 1).repeat(1, nt) # anchor tensor, same as .repeat_interleave(nt)
"""
at:
tensor([[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1],
[2, 2, 2, 2, 2]])
"""
style = 'rect4'
for i in range(det.nl):#nl=3,三层FPN
anchors = det.anchors[i]#det.anchors.shape=3,3,2
gain[2:] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
# Match targets to anchors
a, t, offsets = [], targets * gain, 0
if nt:
r = t[None, :, 4:6] / anchors[:, None] # wh ratio
j = torch.max(r, 1. / r).max(2)[0] < model.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))
a, t = at[j], t.repeat(na, 1, 1)[j] # filter
# overlaps
gxy = t[:, 2:4] # grid xy
z = torch.zeros_like(gxy)
if style == 'rect2':
g = 0.2 # offset
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
a, t = torch.cat((a, a[j], a[k]), 0), torch.cat((t, t[j], t[k]), 0)
offsets = torch.cat((z, z[j] + off[0], z[k] + off[1]), 0) * g
#实际执行以下代码
elif style == 'rect4':
g = 0.5 # offset
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
l, m = ((gxy % 1. > (1 - g)) & (gxy < (gain[[2, 3]] - 1.))).T
a, t = torch.cat((a, a[j], a[k], a[l], a[m]), 0), torch.cat((t, t[j], t[k], t[l], t[m]), 0)
offsets = torch.cat((z, z[j] + off[0], z[k] + off[1], z[l] + off[2], z[m] + off[3]), 0) * g
# 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
indices.append((b, a, gj, gi)) # 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#(3,) (3,) (3, 4) (3,)
def compute_loss(p, targets, model): # predictions, targets, model
ft = torch.cuda.FloatTensor if p[0].is_cuda else torch.Tensor
lcls, lbox, lobj = ft([0]), ft([0]), ft([0])
tcls, tbox, indices, anchors = build_targets(p, targets, model) # targets(3,) (3,) (3, 4) (3,)
h = model.hyp # hyperparameters
red = 'mean' # Loss reduction (sum or mean)
# Define criteria
BCEcls = nn.BCEWithLogitsLoss(pos_weight=ft([h['cls_pw']]), reduction=red)
BCEobj = nn.BCEWithLogitsLoss(pos_weight=ft([h['obj_pw']]), reduction=red)
# class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
cp, cn = smooth_BCE(eps=0.0)
# focal loss
g = h['fl_gamma'] # focal loss gamma
if g > 0:
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
# per output
nt = 0 # targets
for i, pi in enumerate(p): # layer index, layer predictions
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
tobj = torch.zeros_like(pi[..., 0]) # target obj
nb = b.shape[0] # number of targets
if nb:
nt += nb # cumulative targets
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
# GIoU
pxy = ps[:, :2].sigmoid() * 2. - 0.5
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
pbox = torch.cat((pxy, pwh), 1) # predicted box
giou = bbox_iou(pbox.t(), tbox[i], x1y1x2y2=False, GIoU=True) # giou(prediction, target)
lbox += (1.0 - giou).sum() if red == 'sum' else (1.0 - giou).mean() # giou loss
# Obj
tobj[b, a, gj, gi] = (1.0 - model.gr) + model.gr * giou.detach().clamp(0).type(tobj.dtype) # giou ratio
# Class
if model.nc > 1: # cls loss (only if multiple classes)
t = torch.full_like(ps[:, 5:], cn) # targets
t[range(nb), tcls[i]] = cp
lcls += 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)]
lobj += BCEobj(pi[..., 4], tobj) # obj loss
lbox *= h['giou']
lobj *= h['obj']
lcls *= h['cls']
bs = tobj.shape[0] # batch size
if red == 'sum':
g = 3.0 # loss gain
lobj *= g / bs
if nt:
lcls *= g / nt / model.nc
lbox *= g / nt
loss = lbox + lobj + lcls
return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach()
