yolo_darknet_scripts_de_configuration
Différences
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentesRévision précédenteProchaine révision | Révision précédenteProchaine révisionLes deux révisions suivantes | ||
yolo_darknet_scripts_de_configuration [2019/04/07 08:52] – ↷ Nom de la page changé de scripts_de_configuration_yolo_darknet à yolo_darknet_scripts_de_configuration serge | y:yolo_darknet_scripts_de_configuration [2019/05/04 05:59] – ↷ Liens modifiés en raison d'un déplacement. serge | ||
---|---|---|---|
Ligne 1: | Ligne 1: | ||
- | ====== Scripts de configuration | + | ====== |
<WRAP center round box 80% centeralign> | <WRAP center round box 80% centeralign> | ||
//**Le script de configuration yolo-obj.cfg**// | //**Le script de configuration yolo-obj.cfg**// | ||
Ligne 6: | Ligne 6: | ||
**{{tagpage> | **{{tagpage> | ||
</ | </ | ||
- | {{ chappe.jpeg? | + | {{ :chappe.jpeg? |
=====Yolo Darknet sans carte graphique===== | =====Yolo Darknet sans carte graphique===== | ||
- | * Pour **[[yolo_sans_carte_graphique|Yolo Darknet sans carte graphique]]** | + | * Pour **[[y:yolo_sans_carte_graphique|Yolo Darknet sans carte graphique]]** |
* classes=27 | * classes=27 | ||
Ligne 196: | Ligne 196: | ||
- | =====Yolo Darknet sur un portable Optimus===== | ||
- | * Pour **[[yolo_darknet_sur_un_portable_optimus|Yolo Darknet sur un portable Optimus]]** | ||
- | * classes=27 | ||
- | <file ini yolov3-tiny.cfg> | ||
- | à récupérer sur optimus | ||
- | </ | ||
- | {{tag> ia sb semaphore }} | ||
- | =====Yolo Darknet sur Nvidia 1060GTX===== | + | {{tag>sb}} |
- | <file sh yolov3-tiny_obj_labo.cfg> | + | |
- | [net] | + | |
- | # Testing | + | |
- | #batch=1 | + | |
- | # | + | |
- | # Training | + | |
- | batch=64 | + | |
- | subdivisions=64 | + | |
- | width=704 | + | |
- | height=704 | + | |
- | channels=3 | + | |
- | momentum=0.9 | + | |
- | decay=0.0005 | + | |
- | angle=0 | + | |
- | saturation = 1.5 | + | |
- | exposure = 1.5 | + | |
- | hue=.1 | + | |
- | + | ||
- | learning_rate=0.001 | + | |
- | burn_in=1000 | + | |
- | max_batches = 500200 | + | |
- | policy=steps | + | |
- | steps=400000, | + | |
- | scales=.1, | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=16 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=2 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=32 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=2 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=64 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=2 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=128 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=2 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=256 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=2 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=512 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [maxpool] | + | |
- | size=2 | + | |
- | stride=1 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=1024 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | ########### | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=256 | + | |
- | size=1 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=512 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [convolutional] | + | |
- | size=1 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | filters=96 | + | |
- | activation=linear | + | |
- | + | ||
- | [yolo] | + | |
- | mask = 3,4,5 | + | |
- | anchors = 10, | + | |
- | classes=27 | + | |
- | num=6 | + | |
- | jitter=.3 | + | |
- | ignore_thresh = .7 | + | |
- | truth_thresh = 1 | + | |
- | random=1 | + | |
- | + | ||
- | [route] | + | |
- | layers = -4 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=128 | + | |
- | size=1 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [upsample] | + | |
- | stride=2 | + | |
- | + | ||
- | [route] | + | |
- | layers = -1, 8 | + | |
- | + | ||
- | [convolutional] | + | |
- | batch_normalize=1 | + | |
- | filters=256 | + | |
- | size=3 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | activation=leaky | + | |
- | + | ||
- | [convolutional] | + | |
- | size=1 | + | |
- | stride=1 | + | |
- | pad=1 | + | |
- | filters=96 | + | |
- | activation=linear | + | |
- | + | ||
- | [yolo] | + | |
- | mask = 0,1,2 | + | |
- | anchors = 10, | + | |
- | classes=27 | + | |
- | num=6 | + | |
- | jitter=.3 | + | |
- | ignore_thresh = .7 | + | |
- | truth_thresh = 1 | + | |
- | random=1 | + | |
- | </file> | + |
yolo_darknet_scripts_de_configuration.txt · Dernière modification : 2020/10/05 10:39 de serge