adversarial_semseg.py 文件源码

def make_discriminator(self):
        # TODO just to have something, 5 layers vgg-like
        inputs = Input(shape=self.img_shape)
        enc1 = self.downsampling_block_basic(inputs, 64, 7)
        enc2 = self.downsampling_block_basic(enc1,   64, 7)
        enc3 = self.downsampling_block_basic(enc2,   92, 7)
        enc4 = self.downsampling_block_basic(enc3,  128, 7)
        enc5 = self.downsampling_block_basic(enc4,  128, 7)
        flat = Flatten()(enc5)
        dense1 = Dense(512, activation='sigmoid')(flat)
        dense2 = Dense(512, activation='sigmoid')(dense1)
        fake = Dense(1, activation='sigmoid', name='generation')(dense2)
        # Dense(2,... two classes : real and fake
        # change last activation to softmax ?
        discriminator = kmodels.Model(input=inputs, output=fake)

        lr = 1e-04
        optimizer = RMSprop(lr=lr, rho=0.9, epsilon=1e-8, clipnorm=10)
        print ('   Optimizer discriminator: rmsprop. Lr: {}. Rho: 0.9, epsilon=1e-8, '
               'clipnorm=10'.format(lr))

        discriminator.compile(loss='binary_crossentropy', optimizer=optimizer)
        # TODO metrics=metrics,
        return discriminator