November 2019
Intermediate to advanced
346 pages
9h 36m
English
As for most recipes, we begin by importing the necessary libraries. We then load up a MesoNet model in step 2, that is, load up its structure and pre-trained weights. For clarity, the architecture may be found in the MesoNet_classifiers file and is given by the following:
x = Input(shape = (IMGWIDTH, IMGWIDTH, 3)) x1 = Conv2D(8, (3, 3), padding='same', activation = 'relu')(x) x1 = BatchNormalization()(x1) x1 = MaxPooling2D(pool_size=(2, 2), padding='same')(x1) x2 = Conv2D(8, (5, 5), padding='same', activation = 'relu')(x1) x2 = BatchNormalization()(x2) x2 = MaxPooling2D(pool_size=(2, 2), padding='same')(x2) x3 = Conv2D(16, (5, 5), padding='same', activation = 'relu')(x2) x3 = BatchNormalization()(x3) x3 = MaxPooling2D(pool_size=(2, ...