1 files changed, 80 insertions, 73 deletions
diff --git a/ncdcgan.py b/ncdcgan.py
index 7aa7e83..ccb99d3 100755
--- a/ncdcgan.py
+++ b/ncdcgan.py
@@ -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)
-
-        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)
-
-        # Combine the two
-        x = keras.layers.Concatenate()([noise, label])
-
-        x = Conv2DTranspose(256, kernel_size=3, padding="same", strides=(2,2))(x)
-        x = BatchNormalization()(x)
-        x = Activation("relu")(x)
-
-        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)
 
-        x = (Conv2DTranspose(1, kernel_size=3, padding="same"))(x)
-        x = Activation("tanh")(x)
+    def build_generator(self, noise, con):
 
-        model = Model(inputs=[noise, label], outputs=x)
+        n_channel = 64
+        kernel_size = 3
 
-        model.summary()
+        con1 = Dense(n_channel, activation='tanh')(con) #model settings
+        con1 = Reshape((1,1,n_channel))(con1)
+        con1 = UpSampling2D((28,28))(con1)
 
+        hid = Dense(n_channel*7*7, activation='relu')(noise)
+        hid = Reshape((7,7,n_channel))(hid)
+
+        hid = Conv2DTranspose(n_channel, kernel_size=kernel_size, strides=2, padding="same")(hid)
+        hid = BatchNormalization(momentum=0.8)(hid)
+        hid = Activation("relu")(hid)
+
+        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])
+
+        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(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
 
-        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'))
+        con1 = Dense(n_channel, activation='tanh')(con) #model settings
+        con1 = Reshape((1,1,n_channel))(con1)
+        con1 = UpSampling2D((28,28))(con1)
 
-        #model.summary()
 
-        img = Input(shape=self.img_shape)
+        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
 
-        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)
+        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])
 
-        model_input = multiply([flat_img, label_embedding])
 
-        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) # -> 64
 
-        return Model([img, label], validity)
+        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
+
+        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)
 '''
-