YAML reformat (#12648)

* YAML reformat

* Auto-format by Ultralytics actions

---------

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>

data/Argoverse.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── Argoverse  ← downloads here (31.3 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/Argoverse  # dataset root dir
-train: Argoverse-1.1/images/train/  # train images (relative to 'path') 39384 images
-val: Argoverse-1.1/images/val/  # val images (relative to 'path') 15062 images
-test: Argoverse-1.1/images/test/  # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
+path: ../datasets/Argoverse # dataset root dir
+train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
+val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
+test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
 
 # Classes
 names:
@@ -24,7 +23,6 @@ names:
   6: traffic_light
   7: stop_sign
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json

data/GlobalWheat2020.yaml

@@ -6,9 +6,8 @@
 # └── datasets
 #     └── GlobalWheat2020  ← downloads here (7.0 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/GlobalWheat2020  # dataset root dir
+path: ../datasets/GlobalWheat2020 # dataset root dir
 train: # train images (relative to 'path') 3422 images
   - images/arvalis_1
   - images/arvalis_2
@@ -29,7 +28,6 @@ test: # test images (optional) 1276 images
 names:
   0: wheat_head
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from utils.general import download, Path

data/ImageNet.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── imagenet  ← downloads here (144 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/imagenet  # dataset root dir
-train: train  # train images (relative to 'path') 1281167 images
-val: val  # val images (relative to 'path') 50000 images
-test:  # test images (optional)
+path: ../datasets/imagenet # dataset root dir
+train: train # train images (relative to 'path') 1281167 images
+val: val # val images (relative to 'path') 50000 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -1017,6 +1016,5 @@ names:
   998: ear
   999: toilet paper
 
-
 # Download script/URL (optional)
 download: data/scripts/get_imagenet.sh

data/ImageNet10.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── imagenet10  ← downloads here
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/imagenet10  # dataset root dir
-train: train  # train images (relative to 'path') 1281167 images
-val: val  # val images (relative to 'path') 50000 images
-test:  # test images (optional)
+path: ../datasets/imagenet10 # dataset root dir
+train: train # train images (relative to 'path') 1281167 images
+val: val # val images (relative to 'path') 50000 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -27,6 +26,5 @@ names:
   8: hen
   9: ostrich
 
-
 # Download script/URL (optional)
 download: data/scripts/get_imagenet10.sh

data/ImageNet100.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── imagenet100  ← downloads here
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/imagenet100  # dataset root dir
-train: train  # train images (relative to 'path') 1281167 images
-val: val  # val images (relative to 'path') 50000 images
-test:  # test images (optional)
+path: ../datasets/imagenet100 # dataset root dir
+train: train # train images (relative to 'path') 1281167 images
+val: val # val images (relative to 'path') 50000 images
+test: # test images (optional)
 
 # Classes
 names:

data/ImageNet1000.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── imagenet100  ← downloads here
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/imagenet1000  # dataset root dir
-train: train  # train images (relative to 'path') 1281167 images
-val: val  # val images (relative to 'path') 50000 images
-test:  # test images (optional)
+path: ../datasets/imagenet1000 # dataset root dir
+train: train # train images (relative to 'path') 1281167 images
+val: val # val images (relative to 'path') 50000 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -1017,6 +1016,5 @@ names:
   998: ear
   999: toilet paper
 
-
 # Download script/URL (optional)
 download: data/scripts/get_imagenet1000.sh

data/Objects365.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── Objects365  ← downloads here (712 GB = 367G data + 345G zips)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/Objects365  # dataset root dir
-train: images/train  # train images (relative to 'path') 1742289 images
+path: ../datasets/Objects365 # dataset root dir
+train: images/train # train images (relative to 'path') 1742289 images
 val: images/val # val images (relative to 'path') 80000 images
-test:  # test images (optional)
+test: # test images (optional)
 
 # Classes
 names:
@@ -381,7 +380,6 @@ names:
   363: Curling
   364: Table Tennis
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from tqdm import tqdm

data/SKU-110K.yaml

@@ -6,18 +6,16 @@
 # └── datasets
 #     └── SKU-110K  ← downloads here (13.6 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/SKU-110K  # dataset root dir
-train: train.txt  # train images (relative to 'path')  8219 images
-val: val.txt  # val images (relative to 'path')  588 images
-test: test.txt  # test images (optional)  2936 images
+path: ../datasets/SKU-110K # dataset root dir
+train: train.txt # train images (relative to 'path')  8219 images
+val: val.txt # val images (relative to 'path')  588 images
+test: test.txt # test images (optional)  2936 images
 
 # Classes
 names:
   0: object
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import shutil

data/VOC.yaml

@@ -6,7 +6,6 @@
 # └── datasets
 #     └── VOC  ← downloads here (2.8 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
 path: ../datasets/VOC
 train: # train images (relative to 'path')  16551 images
@@ -42,7 +41,6 @@ names:
   18: train
   19: tvmonitor
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import xml.etree.ElementTree as ET

data/VisDrone.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── VisDrone  ← downloads here (2.3 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/VisDrone  # dataset root dir
-train: VisDrone2019-DET-train/images  # train images (relative to 'path')  6471 images
-val: VisDrone2019-DET-val/images  # val images (relative to 'path')  548 images
-test: VisDrone2019-DET-test-dev/images  # test images (optional)  1610 images
+path: ../datasets/VisDrone # dataset root dir
+train: VisDrone2019-DET-train/images # train images (relative to 'path')  6471 images
+val: VisDrone2019-DET-val/images # val images (relative to 'path')  548 images
+test: VisDrone2019-DET-test-dev/images # test images (optional)  1610 images
 
 # Classes
 names:
@@ -26,7 +25,6 @@ names:
   8: bus
   9: motor
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from utils.general import download, os, Path

data/coco.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── coco  ← downloads here (20.1 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco  # dataset root dir
-train: train2017.txt  # train images (relative to 'path') 118287 images
-val: val2017.txt  # val images (relative to 'path') 5000 images
-test: test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+path: ../datasets/coco # dataset root dir
+train: train2017.txt # train images (relative to 'path') 118287 images
+val: val2017.txt # val images (relative to 'path') 5000 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
 
 # Classes
 names:
@@ -96,7 +95,6 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: |
   from utils.general import download, Path

data/coco128-seg.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── coco128-seg  ← downloads here (7 MB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco128-seg  # dataset root dir
-train: images/train2017  # train images (relative to 'path') 128 images
-val: images/train2017  # val images (relative to 'path') 128 images
-test:  # test images (optional)
+path: ../datasets/coco128-seg # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -96,6 +95,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco128-seg.zip

data/coco128.yaml

@@ -6,12 +6,11 @@
 # └── datasets
 #     └── coco128  ← downloads here (7 MB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco128  # dataset root dir
-train: images/train2017  # train images (relative to 'path') 128 images
-val: images/train2017  # val images (relative to 'path') 128 images
-test:  # test images (optional)
+path: ../datasets/coco128 # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -96,6 +95,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco128.zip

data/hyps/hyp.no-augmentation.yaml

@@ -3,33 +3,33 @@
 # python train.py --hyp hyp.no-augmentation.yaml
 # See https://github.com/ultralytics/yolov5/pull/3882 for YOLOv5 + Albumentations Usage examples
 
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.1  # 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: 0.3  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 0.7  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
+lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1 # 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: 0.3 # cls loss gain
+cls_pw: 1.0 # cls BCELoss positive_weight
+obj: 0.7 # obj loss gain (scale with pixels)
+obj_pw: 1.0 # obj BCELoss positive_weight
+iou_t: 0.20 # IoU training threshold
+anchor_t: 4.0 # anchor-multiple threshold
 # anchors: 3  # anchors per output layer (0 to ignore)
 # this parameters are all zero since we want to use albumentation framework
-fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
-hsv_h: 0  # image HSV-Hue augmentation (fraction)
-hsv_s: 0  # image HSV-Saturation augmentation (fraction)
-hsv_v: 0  # image HSV-Value augmentation (fraction)
-degrees: 0.0  # image rotation (+/- deg)
-translate: 0  # image translation (+/- fraction)
-scale: 0  # image scale (+/- gain)
-shear: 0  # image shear (+/- deg)
-perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
-flipud: 0.0  # image flip up-down (probability)
-fliplr: 0.0  # image flip left-right (probability)
-mosaic: 0.0  # image mosaic (probability)
-mixup: 0.0  # image mixup (probability)
-copy_paste: 0.0  # segment copy-paste (probability)
+fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0 # image HSV-Hue augmentation (fraction)
+hsv_s: 0 # image HSV-Saturation augmentation (fraction)
+hsv_v: 0 # image HSV-Value augmentation (fraction)
+degrees: 0.0 # image rotation (+/- deg)
+translate: 0 # image translation (+/- fraction)
+scale: 0 # image scale (+/- gain)
+shear: 0 # image shear (+/- deg)
+perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0 # image flip up-down (probability)
+fliplr: 0.0 # image flip left-right (probability)
+mosaic: 0.0 # image mosaic (probability)
+mixup: 0.0 # image mixup (probability)
+copy_paste: 0.0 # segment copy-paste (probability)

data/hyps/hyp.scratch-high.yaml

@@ -3,32 +3,32 @@
 # python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
 # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
 
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.1  # 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: 0.3  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 0.7  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
+lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1 # 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: 0.3 # cls loss gain
+cls_pw: 1.0 # cls BCELoss positive_weight
+obj: 0.7 # obj loss gain (scale with pixels)
+obj_pw: 1.0 # obj BCELoss positive_weight
+iou_t: 0.20 # IoU training threshold
+anchor_t: 4.0 # anchor-multiple threshold
 # anchors: 3  # anchors per output layer (0 to ignore)
-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: 0.9  # 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: 0.1  # image mixup (probability)
-copy_paste: 0.1  # segment copy-paste (probability)
+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: 0.9 # 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: 0.1 # image mixup (probability)
+copy_paste: 0.1 # segment copy-paste (probability)

data/hyps/hyp.scratch-low.yaml

@@ -3,32 +3,32 @@
 # python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
 # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
 
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.01  # 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_pw: 1.0  # cls BCELoss positive_weight
-obj: 1.0  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
+lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.01 # 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_pw: 1.0 # cls BCELoss positive_weight
+obj: 1.0 # obj loss gain (scale with pixels)
+obj_pw: 1.0 # obj BCELoss positive_weight
+iou_t: 0.20 # IoU training threshold
+anchor_t: 4.0 # anchor-multiple threshold
 # anchors: 3  # anchors per output layer (0 to ignore)
-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)
+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)

data/hyps/hyp.scratch-med.yaml

@@ -3,32 +3,32 @@
 # python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
 # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
 
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.1  # 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: 0.3  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 0.7  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
+lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1 # 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: 0.3 # cls loss gain
+cls_pw: 1.0 # cls BCELoss positive_weight
+obj: 0.7 # obj loss gain (scale with pixels)
+obj_pw: 1.0 # obj BCELoss positive_weight
+iou_t: 0.20 # IoU training threshold
+anchor_t: 4.0 # anchor-multiple threshold
 # anchors: 3  # anchors per output layer (0 to ignore)
-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: 0.9  # 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: 0.1  # image mixup (probability)
-copy_paste: 0.0  # segment copy-paste (probability)
+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: 0.9 # 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: 0.1 # image mixup (probability)
+copy_paste: 0.0 # segment copy-paste (probability)

data/xView.yaml

@@ -7,11 +7,10 @@
 # └── datasets
 #     └── xView  ← downloads here (20.7 GB)
 
-
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/xView  # dataset root dir
-train: images/autosplit_train.txt  # train images (relative to 'path') 90% of 847 train images
-val: images/autosplit_val.txt  # train images (relative to 'path') 10% of 847 train images
+path: ../datasets/xView # dataset root dir
+train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
+val: images/autosplit_val.txt # train images (relative to 'path') 10% of 847 train images
 
 # Classes
 names:
@@ -76,7 +75,6 @@ names:
   58: Pylon
   59: Tower
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json