10月2日 炼丹

李志颖

日志记录：10月2日下午22:27 代号：001

:::info 数据：
cls loss 从0.5到0.25 obj loss从1到0.7
命令行：
python train.py —weights weights/yolov5s6.pt —cfg models/yolov5s6-bifpn_atten.yaml —hyp da️️️ta/hyps/hyp.clothes29.yaml —data dataSet/clothes.yaml —batch-size 64 —epochs 60 —device 1,3,5,6 :::

lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.05 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.937 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
warmup_bias_lr: 0.1 # warmup initial bias lr
box: 0.05 # box loss gain
#cls: 0.5 # cls loss gain
cls: 0.25 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
#obj: 0.5 # obj loss gain (scale with pixels)
obj: 0.7 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
#iou_t: 0.3 # IoU training threshold
iou_t: 0.22 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_eiou_gamma: 0.0 #focal eiou loss gamma
iou_aware: 0.0
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

赵容

陈唯彬

任奕帆

杨淯而

罗宇鑫

:::info 今日总结：4份数据
warmup_bias_lr 优值在0.055附近
最优图数据为：
warmup_bias_lr 0.055 :::

日志记录：10月2日下午18:00 代号：001

:::info 数据：
warmup_bias_lr从 0.1 下降到0.07
命令行：
python train.py —weights weights/yolov5s.pt —cfg models/yolov5s6-bifpn_atten.yaml —data dataSet/clothes.yaml —hyp data/hyps/hyp.clother001.yaml —batch-size 36 —epochs 70 —device 0 :::
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.05 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.900 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
#warmup_bias_lr: 0.1 # warmup initial bias lr
warmup_bias_lr: 0.07 # warmup initial bias lr
box: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 0.5 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.30 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_eiou_gamma: 0.0 #focal eiou loss gamma
iou_aware: 0.0
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

日志记录：10月2日下午20:00 代号：002

:::info 数据：
warmup_bias_lr从 0.07 下降到0.04
命令行：
python train.py —weights weights/yolov5s.pt —cfg models/yolov5s6-bifpn_atten.yaml —data dataSet/clothes.yaml —hyp data/hyps/hyp.clothe002.yaml —batch-size 36 —epochs 70 —device 0 :::
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.05 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.900 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
#warmup_bias_lr: 0.07 # warmup initial bias lr
warmup_bias_lr: 0.04 # warmup initial bias lr
box: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 0.5 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.30 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_eiou_gamma: 0.0 #focal eiou loss gamma
iou_aware: 0.0
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

日志记录：10月2日下午22:00 代号：003

:::info 数据：
warmup_bias_lr从 0.04 下降到0.01
命令行：
python train.py —weights weights/yolov5s.pt —cfg models/yolov5s6-bifpn_atten.yaml —data dataSet/clothes.yaml —hyp data/hyps/hyp.clothe004.yaml —batch-size 64 —epochs 70 —device 0,1 :::
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.05 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.900 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
#warmup_bias_lr: 0.04 # warmup initial bias lr
warmup_bias_lr: 0.01 # warmup initial bias lr
box: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 0.5 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.30 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_eiou_gamma: 0.0 #focal eiou loss gamma
iou_aware: 0.0
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

日志记录：10月2日下午22:00 代号：004

:::info 数据：
warmupbias_lr从 0.01 恢复到0.055
命令行：
python train.py —weights weights/yolov5s.pt —cfg models/yolov5s6-bifpn_atten.yaml —data dataSet/clothes.yaml —hyp data/hyps/hyp.clothe002.yaml —batch-size 24 —epochs 70 —device 7 ::: �
lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.05 # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.900 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
#warmup_bias_lr: 0.01 # warmup initial bias lr
warmup_bias_lr: 0.055 # warmup initial bias lr
box: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 0.5 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.30 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3 # anchors per output layer (0 to ignore)
fl_eiou_gamma: 0.0 #focal eiou loss gamma
iou_aware: 0.0
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)

�