what does x = (....)(x) do?
from my guess: (x) is the input for that line
FYI: I know the only basics of python(e.g. function, method, for/while loops, if/with/and/... statement and the basic structure of Q-learning and neural_network
def network(input_shape, num_classes):
img_input = Input(shape=input_shape, name='data')
x = Lambda(convert_to_hsv_and_grayscale)(img_input)
x = Conv2D(16, (5, 5), strides=(1, 1), padding='same', name='conv1')(x)
x = Activation('relu', name='conv1_relu')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='valid', name='pool1')(x)
x = Conv2D(32, (5, 5), strides=(1, 1), padding='same', name='conv2')(x)
x = Activation('relu', name='conv2_relu')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='valid', name='pool2')(x)
x = Conv2D(64, (5, 5), strides=(1, 1), padding='same', name='conv3')(x)
x = Activation('relu', name='conv3_relu')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='valid', name='pool3')(x)
x = Conv2D(128, (5, 5), strides=(1, 1), padding='same', name='conv4')(x)
x = Activation('relu', name='conv4_relu')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='valid', name='pool4')(x)
x = Flatten()(x)
x = Dense(1024, activation='relu', name='fcl1')(x)
x = Dropout(0.2)(x)
x = Dense(256, activation='relu', name='fcl2')(x)
x = Dropout(0.2)(x)
out = Dense(num_classes, activation='softmax', name='predictions')(x)
rez = Model(inputs=img_input, outputs=out)
return rez
