Différences

Ci-dessous, les différences entre deux révisions de la page.

--- yolo_darknet_sur_un_gros_centre_de_calcul [2019/04/06 14:08] – [Yolo v3 tiny] serge
+++ yolo_darknet_sur_un_gros_centre_de_calcul [2019/04/09 11:03] (Version actuelle) – supprimée serge
@@ Ligne 1: / Ligne 1: @@
-====== Yolo Darknet sur un gros centre de calcul ======
-<WRAP center round box 80% centeralign>
-//**Yolo v3 avec une bonne carte graphique Nvidia 1060 GTX**//
-</WRAP>
-<WRAP center round box 80% centeralign>
-**{{tagpage>semaphore|Sémaphores}}**  ....  **{{tagpage>bge|Blender Game Engine}}** ....  **{{tagpage>ia|Intelligence Artificielle}}**
-</WRAP>
-{{ chappe.jpeg?400 }}
-=====Ressources et documentation de YOLO Darknet=====
-===Darknet===
-  * **[[https://github.com/AlexeyAB/darknet|darknet de AlexeyAB sur GitHub]] **
-=====Training=====
-Idem à **[[yolo_darknet_sur_un_portable_optimus|Yolo Darknet sur un portable Optimus]]** mais avec 64000 images 704x704 au lieu de 1000 images 416*416
-{{ :2019_04:shot_2382_f.jpg?400 |}}
-====Yolo v3=====
-  * [[https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects|How to train (to detect your custom objects) Training Yolo v3]]
-  *
-Il faut une carte graphique avec 4Go de RAM Minimum:
-  export PATH=/usr/local/cuda-10.0/bin${PATH:+:${PATH}}
-   ./darknet detector train cfg/obj.data cfg/yolo-obj.cfg darknet53.conv.74 -map
-Plantage après quelques heures.
-====Yolo v3 tiny====
-  * [[https://github.com/AlexeyAB/darknet#how-to-train-tiny-yolo-to-detect-your-custom-objects|How to train tiny-yolo (to detect your custom objects) ]]
-{{ :2019_04:yolo_labo_v3_tiny.png?1000 |}}
-<file sh yolov3-tiny_obj_labo.cfg>
-[net]
-# Testing
-#batch=1
-#subdivisions=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=400000,450000
-scales=.1,.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 = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
-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 = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
-classes=27
-num=6
-jitter=.3
-ignore_thresh = .7
-truth_thresh = 1
-random=1
-</file>
-  export PATH=/usr/local/cuda-10.0/bin${PATH:+:${PATH}}
-  ./darknet partial cfg/yolov3-tiny.cfg yolov3-tiny.weights yolov3-tiny.conv.15 15
-  ./darknet detector train cfg/obj.data cfg/yolov3-tiny_obj_labo.cfg yolov3-tiny.conv.15 -map
-{{tag> ia sb semaphore }}