diff options
Diffstat (limited to 'ncdcgan.py')
| -rwxr-xr-x | ncdcgan.py | 143 |
1 files changed, 75 insertions, 68 deletions
@@ -4,7 +4,7 @@ import tensorflow as keras import tensorflow as tf import tensorflow.keras as keras from keras.datasets import mnist -from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply +from keras.layers import Input, Dense, Reshape, Flatten, Dropout, Multiply from keras.layers import BatchNormalization, Embedding, Activation, ZeroPadding2D from keras.layers import LeakyReLU from keras.layers import UpSampling2D, Conv2D, Conv2DTranspose @@ -33,19 +33,24 @@ class nCDCGAN(): optimizer = Adam(0.002, 0.5) + noise = Input(shape=(self.latent_dim,)) + label = Input(shape=(1,)) + + # Build the generator + self.generator = self.build_generator(noise, label) + + ph_img = Input(shape=self.img_shape) + # Build and compile the discriminator - self.discriminator = self.build_discriminator() + self.discriminator = self.build_discriminator(ph_img, label) self.discriminator.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy']) - # Build the generator - self.generator = self.build_generator() - - noise = Input(shape=(self.latent_dim,)) - label = Input(shape=(1,)) img = self.generator([noise, label]) + + # For the combined model we will only train the generator self.discriminator.trainable = False @@ -59,86 +64,89 @@ class nCDCGAN(): self.combined.compile(loss=['binary_crossentropy'], optimizer=optimizer) - def build_generator(self): - noise = Input(shape=(self.latent_dim,)) - label = Input(shape=(1,), dtype='int32') - label = Flatten()(Embedding(self.num_classes, self.latent_dim)(label)) - noise = Dense(7 * 7 * 256)(noise) - noise = Reshape(target_shape=(7, 7, 256))(noise) - noise = Conv2DTranspose(256, kernel_size=3, padding="same")(noise) - noise = BatchNormalization()(noise) - noise = Activation("relu")(noise) + def build_generator(self, noise, con): - label = Dense(7 * 7 * 256)(label) - label = Reshape(target_shape=(7, 7, 256))(label) - label = Conv2DTranspose(256, kernel_size=3, padding="same")(label) - label = BatchNormalization()(label) - label = Activation("relu")(label) + n_channel = 64 + kernel_size = 3 - # Combine the two - x = keras.layers.Concatenate()([noise, label]) + con1 = Dense(n_channel, activation='tanh')(con) #model settings + con1 = Reshape((1,1,n_channel))(con1) + con1 = UpSampling2D((28,28))(con1) - x = Conv2DTranspose(256, kernel_size=3, padding="same", strides=(2,2))(x) - x = BatchNormalization()(x) - x = Activation("relu")(x) + hid = Dense(n_channel*7*7, activation='relu')(noise) + hid = Reshape((7,7,n_channel))(hid) - x = Conv2DTranspose(128, kernel_size=3, padding="same", strides=(2,2))(x) - x = BatchNormalization()(x) - x = Activation("relu")(x) - - x = Conv2DTranspose(64, kernel_size=3, padding="same", strides=(2,2))(x) - x = BatchNormalization()(x) - x = Activation("relu")(x) + hid = Conv2DTranspose(n_channel, kernel_size=kernel_size, strides=2, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = Activation("relu")(hid) - x = (Conv2DTranspose(1, kernel_size=3, padding="same"))(x) - x = Activation("tanh")(x) + hid = Conv2DTranspose(n_channel, kernel_size=kernel_size, strides=2, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = Activation("relu")(hid) # -> 128x144x144 + hid = Multiply()([hid, con1]) - model = Model(inputs=[noise, label], outputs=x) + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=1, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = Activation("relu")(hid) # -> 128x144x144 + hid = Multiply()([hid, con1]) - model.summary() + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=1, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = Activation("relu")(hid) # -> 128x144x144 + hid = Multiply()([hid, con1]) + + hid = Conv2D(1, kernel_size=kernel_size, strides=1, padding="same")(hid) + out = Activation("tanh")(hid) + model = Model([noise, con], out) + model.summary() return model - def build_discriminator(self): - model = Sequential() + def build_discriminator(self, img, con): + + n_channel = 64 + kernel_size = 3 + + con1 = Dense(n_channel, activation='tanh')(con) #model settings + con1 = Reshape((1,1,n_channel))(con1) + con1 = UpSampling2D((28,28))(con1) - model.add(Dense(28 * 28 * 3, activation="relu")) - model.add(Reshape((28, 28, 3))) - model.add(Conv2D(32, kernel_size=3, strides=2, padding="same")) - model.add(LeakyReLU(alpha=0.2)) - model.add(Dropout(0.25)) - model.add(Conv2D(64, kernel_size=3, strides=2, padding="same")) - model.add(ZeroPadding2D(padding=((0,1),(0,1)))) - model.add(BatchNormalization()) - model.add(LeakyReLU(alpha=0.2)) - model.add(Dropout(0.25)) - model.add(Conv2D(128, kernel_size=3, strides=2, padding="same")) - model.add(BatchNormalization()) - model.add(LeakyReLU(alpha=0.2)) - model.add(Dropout(0.25)) - model.add(Conv2D(256, kernel_size=3, strides=1, padding="same")) - model.add(BatchNormalization()) - model.add(LeakyReLU(alpha=0.2)) - model.add(Dropout(0.25)) - model.add(Flatten()) - model.add(Dense(1, activation='sigmoid')) - #model.summary() + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=1, padding="same")(img) + hid = BatchNormalization(momentum=0.8)(hid) + hid = LeakyReLU(alpha=0.2)(hid) # -> 32 + hid = Multiply()([hid, con1]) # -> 128x128xn_channel - img = Input(shape=self.img_shape) + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=1, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = LeakyReLU(alpha=0.2)(hid) # -> 32 + hid = Multiply()([hid, con1]) - label = Input(shape=(1,), dtype='int32') + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=1, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = LeakyReLU(alpha=0.2)(hid) # -> 32 + hid = Multiply()([hid, con1]) - label_embedding = Flatten()(Embedding(self.num_classes, np.prod(self.img_shape))(label)) - flat_img = Flatten()(img) - model_input = multiply([flat_img, label_embedding]) + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=2, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = LeakyReLU(alpha=0.2)(hid) # -> 64 - validity = model(model_input) + hid = Conv2D(n_channel, kernel_size=kernel_size, strides=2, padding="same")(hid) + hid = BatchNormalization(momentum=0.8)(hid) + hid = LeakyReLU(alpha=0.2)(hid) # -> 32 - return Model([img, label], validity) + hid = Flatten()(hid) + + hid = Dropout(0.1)(hid) + + out = Dense(1, activation='sigmoid')(hid) + + model = Model(inputs=[img, con], outputs=out) + model.summary() + return model def train(self, epochs, batch_size=128, sample_interval=50, graph=False, smooth_real=1, smooth_fake=0): @@ -255,4 +263,3 @@ if __name__ == '__main__': cdcgan = nCDCGAN() cdcgan.train(epochs=4000, batch_size=32) ''' - |