Lien de la note Hackmd
Un reseau de neurones convolutif
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Continue 1D:
Discrete 2D:
est l'aimeg, le noyau, son support est
Exemple de noyaux (WP Noyau_(traitement_d'image)):
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Conv2D
L'image d'entree a 3 canaux -> chaque filtre a poids
L'image de sortie a 4 canaux, elle pert 4 pixels dans chaque direction
En details + stride + padding = 'same'
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
- Stride: une facon de reduire la taille d'une image
- padding = 'same': la sortie a la meme taille
Convolution a trous
En anglais: atrous convolution
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Couvre la meme surface qu'un noyau , ou que convolutions a la suite, mais pour un cout moins cher (en poids)
Ne reduit pas la taille de l'image (padding = same
)
Convolution separee
- spatiale: une conv conv.
- profondeur: conv sur couches conv puis conv
Convolution separeee spatiale
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
En pratique on fait:
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Conv separee en profondeur
Ici 3 couches:
- conv + conv
- couches en sortie
Gain de calcul important
perte de representation utilise
MobileNet
La convolution transposee (ou deconvolution)
Convolution: concentre en un pixel un bloc de pixel (fois un noyau)
Conv transposee: distribue un pixel (fois un noyau) a un bloc de pixel
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Mathematiquement les deux sont des convolutions mais la conv. transposee a pour but de simuler l'operation inverse de la conv
Trucs d'architecture
Pooling
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Si on veut augmenter le nombre de couches il faut diminuer la taille de l'image sinon BOOM
On veut une vision multi-echelle il faut diminuer la taille de l'image + ponts.
L'inverse du pooling est kl
Ponts
La grande astuce de ResNet qui leur a permis de tout gagner
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Prog. et retro-prog.
Lors de la retropropagation l'erreur prend le pont et les convolutions les premieres couches sont corrigees
Dropout ou BatchNormalization
Pas besoin de dropout si BatchNormalization
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Evite que les poids importants en bloquent d'autres
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Apres convolution
Avant fonction d'activation
Reduit le besoin de normaliser les donnees
Types de problemes en vision
Semantic segmentation
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
- Classification
- Classification + localisation
- Object detection
- Instance segmentation
U-net (2015)
Separation semantique d'images medicales
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Multi-echelle
Notre projet aujourd'hui !
Copy & crops: ce sont des PONTS
- Ca sert a faire des concatenations
Fonctions d'erreur pour la segmentation
Si chaque image de sortie represente les pixels appartenant a la classe , alors on peut finir avec un softmax
:
- Erreur quadratique
mse
: pente douce, pas d'information d'exclusion
- Entropie croisee:
binary_crossentropy
avec ou
categorical_crossentropy
avec resultats sous la forme pour indiquer la classe
sparse_categorical_crossentropy
avec les classes indiques par des entier
Focal loss
Comme la pente du log est forte, elle favorise les cas simples a detecter. On peut ecraser la courbe de pour aider à trouver les cas difficiles.

Augmenter le nombre de donnees
Souvent c'est bien utile, en particulier lorsqu'on manque de donnees.

Parfois ca rend la tache plus difficile et ca ne marche pas.