Différences

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

--- yolo_darknet_avec_un_vrai_semaphore [2019/10/20 10:16] – [Apprentissage] serge
+++ yolo_darknet_avec_un_vrai_semaphore [2019/10/20 10:22] – [cfg] serge
@@ Ligne 61: / Ligne 61: @@
 ====cfg====
 Relire tout le readme pour bien configurer en particulier:
-  * for training for both small and large objects use modified models: **yolov3-tiny_3l.cfg**
+  * for training for both small and large objects use modified models: **yolov3-tiny_3l.cfg** soit [[https://github.com/sergeLabo/semaphore_blend_yolo/blob/master/darknet/calcul_1/calcul_1_9000_jpg_90_small_var.cfg|calcul_1_9000_jpg_90_small_var.cfg]]
   * If you train the model to distinguish Left and Right objects as separate classes (left/right hand, left/right-turn on road signs, ...) then for disabling flip data augmentation - add flip=0