computer_vision_and_pattern_recognition_segmentation_d_image
Différences
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentesRévision précédenteProchaine révision | Révision précédente | ||
computer_vision_and_pattern_recognition [2019/03/05 10:41] – [Ressources] serge | computer_vision_and_pattern_recognition_segmentation_d_image [2020/12/27 15:04] (Version actuelle) – serge | ||
---|---|---|---|
Ligne 1: | Ligne 1: | ||
- | ====== Computer Vision and Pattern Recognition ====== | + | ====== Computer Vision and Pattern Recognition |
+ | <WRAP center round box 60% centeralign> | ||
+ | **{{tagpage> | ||
+ | </ | ||
+ | <WRAP center round box 60% centeralign> | ||
+ | **[[les_pages_intelligence_artificielle_en_details|Les Pages Intelligence Artificielle en détails]]** | ||
+ | </ | ||
<WRAP center round box 80% centeralign> | <WRAP center round box 80% centeralign> | ||
- | **{{tagpage> | + | **{{tagpage> |
</ | </ | ||
<WRAP group> | <WRAP group> | ||
<WRAP half column> | <WRAP half column> | ||
- | {{: | + | {{ youtube> |
+ | **Une bonne explication de l' | ||
</ | </ | ||
<WRAP half column> | <WRAP half column> | ||
- | {{:2019_03: | + | {{ youtube> |
+ | **Les réseaux de convolution (CNN)** | ||
+ | </ | ||
+ | </ | ||
+ | |||
+ | <WRAP group> | ||
+ | <WRAP half column> | ||
+ | {{ media_01:polarlicht_2.jpg? | ||
+ | </ | ||
+ | <WRAP half column> | ||
+ | {{ media_01: | ||
</ | </ | ||
</ | </ | ||
Ligne 16: | Ligne 33: | ||
Wikipedia dit que la **[[https:// | Wikipedia dit que la **[[https:// | ||
- | La **[[https:// | + | La [[https:// |
+ | =====YOLO===== | ||
+ | {{ youtube> | ||
+ | |||
+ | Yolo v3 est utilisé avec: | ||
+ | * **[[yolo_darknet_avec_un_vrai_semaphore|Yolo Darknet avec un vrai sémaphore]]** | ||
+ | =====Définition de Mask R-CNN===== | ||
+ | |||
+ | Les Perceptron, Perceptron multi-couche, | ||
+ | ====R-CNN==== | ||
+ | **R-CNN** = **R**egional **C**onvolutional **N**eural **N**etwork | ||
+ | |||
+ | ====Mask R-CNN==== | ||
+ | |||
+ | * [[https:// | ||
+ | * [[https:// | ||
+ | |||
+ | =====MASK R-CNN vs YOLO vs Deeplab Xception===== | ||
+ | Un peu de zik: {{ youtube> | ||
+ | * [[https:// | ||
+ | * [[https:// | ||
+ | * [[https:// | ||
=====Ressources===== | =====Ressources===== | ||
- | | + | ====ImageNet==== |
- | * **[[https:// | + | |
+ | |||
+ | ====COCO Common Object in Context==== | ||
+ | | ||
+ | |||
+ | ====ROI==== | ||
+ | **ROI = Region of interest** | ||
+ | |||
+ | | ||
+ | **Mask R-CNN** | ||
+ | * [[https:// | ||
+ | |||
+ | **Region of Interest** pooling (also known as RoI pooling ou Roi) is a variant of max pooling, in which output size is fixed and input rectangle is a parameter. | ||
+ | |||
+ | Pooling is an important component of convolutional neural networks for object detection based on Fast R-CNN architecture. | ||
+ | |||
+ | =====Mask R-CNN de la Société Matterport===== | ||
+ | | ||
+ | Mask R-CNN is based on Feature Pyramid Network (FPN) and a ResNet101 backbone. | ||
+ | * [[https:// | ||
- | [[https:// | + | ===Feature Pyramid Network=== |
+ | * [[https:// | ||
- | [[https:// | + | ===ResNet-101=== |
+ | * [[https:// | ||
+ | * [[https:// | ||
- | {{tag>ia python}} | + | {{tag> ia python |
computer_vision_and_pattern_recognition_segmentation_d_image.1551782506.txt.gz · Dernière modification : 2019/03/05 10:41 de serge