Spaces:
Sleeping
Sleeping
File size: 13,874 Bytes
ce91ea1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 |
import os
import torch
import torch.nn as nn
import torch.nn.functional as F
from utils.general import xywh2xyxy
from utils.metrics import bbox_iou
from utils.tal.anchor_generator import dist2bbox, make_anchors, bbox2dist
from utils.tal.assigner import TaskAlignedAssigner
from utils.torch_utils import de_parallel
def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
# return positive, negative label smoothing BCE targets
return 1.0 - 0.5 * eps, 0.5 * eps
class VarifocalLoss(nn.Module):
# Varifocal loss by Zhang et al. https://arxiv.org/abs/2008.13367
def __init__(self):
super().__init__()
def forward(self, pred_score, gt_score, label, alpha=0.75, gamma=2.0):
weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
with torch.cuda.amp.autocast(enabled=False):
loss = (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(),
reduction="none") * weight).sum()
return loss
class FocalLoss(nn.Module):
# Wraps 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().__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 BboxLoss(nn.Module):
def __init__(self, reg_max, use_dfl=False):
super().__init__()
self.reg_max = reg_max
self.use_dfl = use_dfl
def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
# iou loss
bbox_mask = fg_mask.unsqueeze(-1).repeat([1, 1, 4]) # (b, h*w, 4)
pred_bboxes_pos = torch.masked_select(pred_bboxes, bbox_mask).view(-1, 4)
target_bboxes_pos = torch.masked_select(target_bboxes, bbox_mask).view(-1, 4)
bbox_weight = torch.masked_select(target_scores.sum(-1), fg_mask).unsqueeze(-1)
iou = bbox_iou(pred_bboxes_pos, target_bboxes_pos, xywh=False, CIoU=True)
loss_iou = 1.0 - iou
loss_iou *= bbox_weight
loss_iou = loss_iou.sum() / target_scores_sum
# dfl loss
if self.use_dfl:
dist_mask = fg_mask.unsqueeze(-1).repeat([1, 1, (self.reg_max + 1) * 4])
pred_dist_pos = torch.masked_select(pred_dist, dist_mask).view(-1, 4, self.reg_max + 1)
target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max)
target_ltrb_pos = torch.masked_select(target_ltrb, bbox_mask).view(-1, 4)
loss_dfl = self._df_loss(pred_dist_pos, target_ltrb_pos) * bbox_weight
loss_dfl = loss_dfl.sum() / target_scores_sum
else:
loss_dfl = torch.tensor(0.0).to(pred_dist.device)
return loss_iou, loss_dfl, iou
def _df_loss(self, pred_dist, target):
target_left = target.to(torch.long)
target_right = target_left + 1
weight_left = target_right.to(torch.float) - target
weight_right = 1 - weight_left
loss_left = F.cross_entropy(pred_dist.view(-1, self.reg_max + 1), target_left.view(-1), reduction="none").view(
target_left.shape) * weight_left
loss_right = F.cross_entropy(pred_dist.view(-1, self.reg_max + 1), target_right.view(-1),
reduction="none").view(target_left.shape) * weight_right
return (loss_left + loss_right).mean(-1, keepdim=True)
class ComputeLoss:
# Compute losses
def __init__(self, model, use_dfl=True):
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), reduction='none')
# 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 = FocalLoss(BCEcls, g)
m = de_parallel(model).model[-1] # Detect() module
self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7
self.BCEcls = BCEcls
self.hyp = h
self.stride = m.stride # model strides
self.nc = m.nc # number of classes
self.nl = m.nl # number of layers
self.no = m.no
self.reg_max = m.reg_max
self.device = device
self.assigner = TaskAlignedAssigner(topk=int(os.getenv('YOLOM', 10)),
num_classes=self.nc,
alpha=float(os.getenv('YOLOA', 0.5)),
beta=float(os.getenv('YOLOB', 6.0)))
self.assigner2 = TaskAlignedAssigner(topk=int(os.getenv('YOLOM', 10)),
num_classes=self.nc,
alpha=float(os.getenv('YOLOA', 0.5)),
beta=float(os.getenv('YOLOB', 6.0)))
self.assigner3 = TaskAlignedAssigner(topk=int(os.getenv('YOLOM', 10)),
num_classes=self.nc,
alpha=float(os.getenv('YOLOA', 0.5)),
beta=float(os.getenv('YOLOB', 6.0)))
self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=use_dfl).to(device)
self.bbox_loss2 = BboxLoss(m.reg_max - 1, use_dfl=use_dfl).to(device)
self.bbox_loss3 = BboxLoss(m.reg_max - 1, use_dfl=use_dfl).to(device)
self.proj = torch.arange(m.reg_max).float().to(device) # / 120.0
self.use_dfl = use_dfl
def preprocess(self, targets, batch_size, scale_tensor):
if targets.shape[0] == 0:
out = torch.zeros(batch_size, 0, 5, device=self.device)
else:
i = targets[:, 0] # image index
_, counts = i.unique(return_counts=True)
out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
for j in range(batch_size):
matches = i == j
n = matches.sum()
if n:
out[j, :n] = targets[matches, 1:]
out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor))
return out
def bbox_decode(self, anchor_points, pred_dist):
if self.use_dfl:
b, a, c = pred_dist.shape # batch, anchors, channels
pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
# pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype))
# pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2)
return dist2bbox(pred_dist, anchor_points, xywh=False)
def __call__(self, p, targets, img=None, epoch=0):
loss = torch.zeros(3, device=self.device) # box, cls, dfl
feats = p[1][0] if isinstance(p, tuple) else p[0]
feats2 = p[1][1] if isinstance(p, tuple) else p[1]
feats3 = p[1][2] if isinstance(p, tuple) else p[2]
pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
(self.reg_max * 4, self.nc), 1)
pred_scores = pred_scores.permute(0, 2, 1).contiguous()
pred_distri = pred_distri.permute(0, 2, 1).contiguous()
pred_distri2, pred_scores2 = torch.cat([xi.view(feats2[0].shape[0], self.no, -1) for xi in feats2], 2).split(
(self.reg_max * 4, self.nc), 1)
pred_scores2 = pred_scores2.permute(0, 2, 1).contiguous()
pred_distri2 = pred_distri2.permute(0, 2, 1).contiguous()
pred_distri3, pred_scores3 = torch.cat([xi.view(feats3[0].shape[0], self.no, -1) for xi in feats3], 2).split(
(self.reg_max * 4, self.nc), 1)
pred_scores3 = pred_scores3.permute(0, 2, 1).contiguous()
pred_distri3 = pred_distri3.permute(0, 2, 1).contiguous()
dtype = pred_scores.dtype
batch_size, grid_size = pred_scores.shape[:2]
imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w)
anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)
# targets
targets = self.preprocess(targets, batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy
mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
# pboxes
pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4)
pred_bboxes2 = self.bbox_decode(anchor_points, pred_distri2) # xyxy, (b, h*w, 4)
pred_bboxes3 = self.bbox_decode(anchor_points, pred_distri3) # xyxy, (b, h*w, 4)
target_labels, target_bboxes, target_scores, fg_mask = self.assigner(
pred_scores.detach().sigmoid(),
(pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
anchor_points * stride_tensor,
gt_labels,
gt_bboxes,
mask_gt)
target_labels2, target_bboxes2, target_scores2, fg_mask2 = self.assigner2(
pred_scores2.detach().sigmoid(),
(pred_bboxes2.detach() * stride_tensor).type(gt_bboxes.dtype),
anchor_points * stride_tensor,
gt_labels,
gt_bboxes,
mask_gt)
target_labels3, target_bboxes3, target_scores3, fg_mask3 = self.assigner3(
pred_scores3.detach().sigmoid(),
(pred_bboxes3.detach() * stride_tensor).type(gt_bboxes.dtype),
anchor_points * stride_tensor,
gt_labels,
gt_bboxes,
mask_gt)
target_bboxes /= stride_tensor
target_scores_sum = max(target_scores.sum(), 1)
target_bboxes2 /= stride_tensor
target_scores_sum2 = max(target_scores2.sum(), 1)
target_bboxes3 /= stride_tensor
target_scores_sum3 = max(target_scores3.sum(), 1)
# cls loss
# loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way
loss[1] = 0.25 * self.BCEcls(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE
loss[1] += 0.25 * self.BCEcls(pred_scores2, target_scores2.to(dtype)).sum() / target_scores_sum2 # BCE
loss[1] += self.BCEcls(pred_scores3, target_scores3.to(dtype)).sum() / target_scores_sum3 # BCE
# bbox loss
if fg_mask.sum():
loss[0], loss[2], iou = self.bbox_loss(pred_distri,
pred_bboxes,
anchor_points,
target_bboxes,
target_scores,
target_scores_sum,
fg_mask)
loss[0] *= 0.25
loss[2] *= 0.25
if fg_mask2.sum():
loss0_, loss2_, iou2 = self.bbox_loss2(pred_distri2,
pred_bboxes2,
anchor_points,
target_bboxes2,
target_scores2,
target_scores_sum2,
fg_mask2)
loss[0] += 0.25 * loss0_
loss[2] += 0.25 * loss2_
if fg_mask3.sum():
loss0__, loss2__, iou3 = self.bbox_loss3(pred_distri3,
pred_bboxes3,
anchor_points,
target_bboxes3,
target_scores3,
target_scores_sum3,
fg_mask3)
loss[0] += loss0__
loss[2] += loss2__
loss[0] *= 7.5 # box gain
loss[1] *= 0.5 # cls gain
loss[2] *= 1.5 # dfl gain
return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl)
|