web-dev-qa-db-fra.com

Quelle est la différence entre les fonctions UpSampling2D et Conv2DTranspose dans les keras?

Ici dans ce code UpSampling2D et Conv2DTranspose semblent être utilisés de manière interchangeable. Je veux savoir pourquoi cela se produit.

# u-net model with up-convolution or up-sampling and weighted binary-crossentropy as loss func

from keras.models import Model
from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, concatenate, Conv2DTranspose, BatchNormalization, Dropout
from keras.optimizers import Adam
from keras.utils import plot_model
from keras import backend as K

def unet_model(n_classes=5, im_sz=160, n_channels=8, n_filters_start=32, growth_factor=2, upconv=True,
               class_weights=[0.2, 0.3, 0.1, 0.1, 0.3]):
    droprate=0.25
    n_filters = n_filters_start
    inputs = Input((im_sz, im_sz, n_channels))
    #inputs = BatchNormalization()(inputs)
    conv1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(inputs)
    conv1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    #pool1 = Dropout(droprate)(pool1)

    n_filters *= growth_factor
    pool1 = BatchNormalization()(pool1)
    conv2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool1)
    conv2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    pool2 = Dropout(droprate)(pool2)

    n_filters *= growth_factor
    pool2 = BatchNormalization()(pool2)
    conv3 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool2)
    conv3 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    pool3 = Dropout(droprate)(pool3)

    n_filters *= growth_factor
    pool3 = BatchNormalization()(pool3)
    conv4_0 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool3)
    conv4_0 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv4_0)
    pool4_1 = MaxPooling2D(pool_size=(2, 2))(conv4_0)
    pool4_1 = Dropout(droprate)(pool4_1)

    n_filters *= growth_factor
    pool4_1 = BatchNormalization()(pool4_1)
    conv4_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool4_1)
    conv4_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv4_1)
    pool4_2 = MaxPooling2D(pool_size=(2, 2))(conv4_1)
    pool4_2 = Dropout(droprate)(pool4_2)

    n_filters *= growth_factor
    conv5 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(pool4_2)
    conv5 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv5)

    n_filters //= growth_factor
    if upconv:
        up6_1 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv5), conv4_1])
    else:
        up6_1 = concatenate([UpSampling2D(size=(2, 2))(conv5), conv4_1])
    up6_1 = BatchNormalization()(up6_1)
    conv6_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up6_1)
    conv6_1 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv6_1)
    conv6_1 = Dropout(droprate)(conv6_1)

    n_filters //= growth_factor
    if upconv:
        up6_2 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv6_1), conv4_0])
    else:
        up6_2 = concatenate([UpSampling2D(size=(2, 2))(conv6_1), conv4_0])
    up6_2 = BatchNormalization()(up6_2)
    conv6_2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up6_2)
    conv6_2 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv6_2)
    conv6_2 = Dropout(droprate)(conv6_2)

    n_filters //= growth_factor
    if upconv:
        up7 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv6_2), conv3])
    else:
        up7 = concatenate([UpSampling2D(size=(2, 2))(conv6_2), conv3])
    up7 = BatchNormalization()(up7)
    conv7 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up7)
    conv7 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv7)
    conv7 = Dropout(droprate)(conv7)

    n_filters //= growth_factor
    if upconv:
        up8 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv7), conv2])
    else:
        up8 = concatenate([UpSampling2D(size=(2, 2))(conv7), conv2])
    up8 = BatchNormalization()(up8)
    conv8 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up8)
    conv8 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv8)
    conv8 = Dropout(droprate)(conv8)

    n_filters //= growth_factor
    if upconv:
        up9 = concatenate([Conv2DTranspose(n_filters, (2, 2), strides=(2, 2), padding='same')(conv8), conv1])
    else:
        up9 = concatenate([UpSampling2D(size=(2, 2))(conv8), conv1])
    conv9 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(up9)
    conv9 = Conv2D(n_filters, (3, 3), activation='relu', padding='same')(conv9)

    conv10 = Conv2D(n_classes, (1, 1), activation='sigmoid')(conv9)

    model = Model(inputs=inputs, outputs=conv10)

    def weighted_binary_crossentropy(y_true, y_pred):
        class_loglosses = K.mean(K.binary_crossentropy(y_true, y_pred), axis=[0, 1, 2])
        return K.sum(class_loglosses * K.constant(class_weights))

    model.compile(optimizer=Adam(), loss=weighted_binary_crossentropy)
    return model
machine-learningcomputer-visionconv-neural-networkconvolutiondeconvolution
15
Piyush Chauhan

UpSampling2D n’est qu’une simple mise à l’échelle de l’image en la redimensionnant, donc rien d’intelligent. L'avantage est son pas cher.

Conv2DTranspose est une opération de convolution dont le noyau est appris (comme pour une opération conv2d normale) lors de la formation de votre modèle. L'utilisation de Conv2DTranspose permet également de suréchantillonner ses entrées, mais la principale différence est que le modèle doit apprendre quel est le meilleur suréchantillonnage pour le travail.

EDIT: Lien vers la visualisation de Nice de la convolution transposée: https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d

24
Burton2000