April 2017
Intermediate to advanced
318 pages
7h 40m
English
One way to improve the performance is to define a deeper network with multiple convolutional operations. In this example, we have a sequence of modules:
Followed by a standard dense+dropout+dense. All the activation functions are ReLU.
Let us see the code for the new network:
model = Sequential()model.add(Conv2D(32, (3, 3), padding='same',input_shape=(IMG_ROWS, IMG_COLS, IMG_CHANNELS)))model.add(Activation('relu'))model.add(Conv2D(32, (3, 3), padding='same'))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Conv2D(64, (3, 3), padding='same'))model.add(Activation('relu'))model.add(Conv2D(64, ...Read now
Unlock full access