Merge branch 'master' of skozl.com:e4-gan

1 files changed, 233 insertions, 0 deletions

diff --git a/cdcgan.py b/cdcgan.py
new file mode 100755
index 0000000..aba3669
--- /dev/null
+++ b/cdcgan.py
@@ -0,0 +1,233 @@
+from __future__ import print_function, division
+import tensorflow.keras as keras
+import tensorflow as tf
+from keras.datasets import mnist
+
+import keras.layers as layers
+from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply
+from keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D
+from keras.layers.advanced_activations import LeakyReLU
+from keras.layers.convolutional import UpSampling2D, Conv2D
+from keras.models import Sequential, Model
+from keras.optimizers import Adam
+import matplotlib.pyplot as plt
+from IPython.display import clear_output
+from tqdm import tqdm
+
+import numpy as np
+
+class CDCGAN():
+    def __init__(self):
+        # Input shape
+        self.img_rows = 28
+        self.img_cols = 28
+        self.channels = 1
+        self.img_shape = (self.img_rows, self.img_cols, self.channels)
+        self.num_classes = 10
+        self.latent_dim = 100
+
+        optimizer = Adam(0.0002, 0.5)
+
+        # Build and compile the discriminator
+        self.discriminator = self.build_discriminator()
+
+        self.discriminator.compile(loss=['binary_crossentropy'],
+            optimizer=optimizer,
+            metrics=['accuracy'])
+
+        # Build the generator
+        self.generator = self.build_generator()
+
+        # The generator takes noise and the target label as input
+        # and generates the corresponding digit of that label
+        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
+
+        # The discriminator takes generated image as input and determines validity
+        # and the label of that image
+        valid = self.discriminator([img, label])
+
+        # The combined model  (stacked generator and discriminator)
+        # Trains generator to fool discriminator
+        self.combined = Model([noise, label], valid)
+        self.combined.compile(loss=['binary_crossentropy'],
+            optimizer=optimizer)
+
+    def build_generator(self):
+        # Prepare noise input
+        input_z = layers.Input((100,))
+        dense_z_1 = layers.Dense(1024)(input_z)
+        act_z_1 = layers.Activation("tanh")(dense_z_1)
+        dense_z_2 = layers.Dense(128 * 7 * 7)(act_z_1)
+        bn_z_1 = layers.BatchNormalization()(dense_z_2)
+        reshape_z = layers.Reshape((7, 7, 128), input_shape=(128 * 7 * 7,))(bn_z_1)
+
+        # Prepare Conditional (label) input
+        input_c = layers.Input((1,))
+        dense_c_1 = layers.Dense(1024)(input_c)
+        act_c_1 = layers.Activation("tanh")(dense_c_1)
+        dense_c_2 = layers.Dense(128 * 7 * 7)(act_c_1)
+        bn_c_1 = layers.BatchNormalization()(dense_c_2)
+        reshape_c = layers.Reshape((7, 7, 128), input_shape=(128 * 7 * 7,))(bn_c_1)
+
+        # Combine input source
+        concat_z_c = layers.Concatenate()([reshape_z, reshape_c])
+
+        # Image generation with the concatenated inputs
+        up_1 = layers.UpSampling2D(size=(2, 2))(concat_z_c)
+        conv_1 = layers.Conv2D(64, (5, 5), padding='same')(up_1)
+        act_1 = layers.Activation("tanh")(conv_1)
+        up_2 = layers.UpSampling2D(size=(2, 2))(act_1)
+        conv_2 = layers.Conv2D(1, (5, 5), padding='same')(up_2)
+        act_2 = layers.Activation("tanh")(conv_2)
+        model = Model(inputs=[input_z, input_c], outputs=act_2)
+        return model
+
+
+    def build_discriminator(self):
+        input_gen_image = layers.Input((28, 28, 1))
+        conv_1_image = layers.Conv2D(64, (5, 5), padding='same')(input_gen_image)
+        act_1_image = layers.Activation("tanh")(conv_1_image)
+        pool_1_image = layers.MaxPooling2D(pool_size=(2, 2))(act_1_image)
+        conv_2_image = layers.Conv2D(128, (5, 5))(pool_1_image)
+        act_2_image = layers.Activation("tanh")(conv_2_image)
+        pool_2_image = layers.MaxPooling2D(pool_size=(2, 2))(act_2_image)
+
+        input_c = layers.Input((1,))
+        dense_1_c = layers.Dense(1024)(input_c)
+        act_1_c = layers.Activation("tanh")(dense_1_c)
+        dense_2_c = layers.Dense(5 * 5 * 128)(act_1_c)
+        bn_c = layers.BatchNormalization()(dense_2_c)
+        reshaped_c = layers.Reshape((5, 5, 128))(bn_c)
+
+        concat = layers.Concatenate()([pool_2_image, reshaped_c])
+
+        flat = layers.Flatten()(concat)
+        dense_1 = layers.Dense(1024)(flat)
+        act_1 = layers.Activation("tanh")(dense_1)
+        dense_2 = layers.Dense(1)(act_1)
+        act_2 = layers.Activation('sigmoid')(dense_2)
+        model = Model(inputs=[input_gen_image, input_c], outputs=act_2)
+        return model
+
+    def train(self, epochs, batch_size=128, sample_interval=50, graph=False, smooth_real=1, smooth_fake=0):
+
+        # Load the dataset
+        (X_train, y_train), (_, _) = mnist.load_data()
+
+        # Configure input
+        X_train = (X_train.astype(np.float32) - 127.5) / 127.5
+        X_train = np.expand_dims(X_train, axis=3)
+        y_train = y_train.reshape(-1, 1)
+
+        # Adversarial ground truths
+        valid = np.ones((batch_size, 1))
+        fake = np.zeros((batch_size, 1))
+        
+        xaxis = np.arange(epochs)
+        loss = np.zeros((2,epochs))
+        for epoch in tqdm(range(epochs)):
+
+            # ---------------------
+            #  Train Discriminator
+            # ---------------------
+
+            # Select a random half batch of images
+            idx = np.random.randint(0, X_train.shape[0], batch_size)
+            imgs, labels = X_train[idx], y_train[idx]
+
+            # Sample noise as generator input
+            noise = np.random.normal(0, 1, (batch_size, 100))
+
+            # Generate a half batch of new images
+            gen_imgs = self.generator.predict([noise, labels])
+
+            # Train the discriminator
+            d_loss_real = self.discriminator.train_on_batch([imgs, labels], valid*smooth_real)
+            d_loss_fake = self.discriminator.train_on_batch([gen_imgs, labels], valid*smooth_fake)
+            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
+
+            # ---------------------
+            #  Train Generator
+            # ---------------------
+
+            # Condition on labels
+            sampled_labels = np.random.randint(0, 10, batch_size).reshape(-1, 1)
+            # Train the generator
+            g_loss = self.combined.train_on_batch([noise, sampled_labels], valid)
+
+            # Plot the progress
+            #print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
+            loss[0][epoch] = d_loss[0]
+            loss[1][epoch] = g_loss
+
+            # If at save interval => save generated image samples
+            if epoch % sample_interval == 0:
+                self.sample_images(epoch)
+            
+        if graph:
+          plt.plot(xaxis,loss[0])
+          plt.plot(xaxis,loss[1])
+          plt.legend(('Discriminator', 'Generator'), loc='best')
+          plt.xlabel('Epoch')
+          plt.ylabel('Binary Crossentropy Loss')
+
+    def sample_images(self, epoch):
+        r, c = 2, 5
+        noise = np.random.normal(0, 1, (r * c, 100))
+        sampled_labels = np.arange(0, 10).reshape(-1, 1)
+
+        #using dummy_labels would just print zeros to help identify image quality
+        #dummy_labels = np.zeros(32).reshape(-1, 1)
+        
+        gen_imgs = self.generator.predict([noise, sampled_labels])
+
+        # Rescale images 0 - 1
+        gen_imgs = 0.5 * gen_imgs + 0.5
+
+        fig, axs = plt.subplots(r, c)
+        cnt = 0
+        for i in range(r):
+            for j in range(c):
+                axs[i,j].imshow(gen_imgs[cnt,:,:,0], cmap='gray')
+                axs[i,j].set_title("Digit: %d" % sampled_labels[cnt])
+                axs[i,j].axis('off')
+                cnt += 1
+        fig.savefig("images/%d.png" % epoch)
+        plt.close()
+        
+    def generate_data(self):
+      noise_train = np.random.normal(0, 1, (55000, 100))
+      noise_test = np.random.normal(0, 1, (10000, 100))
+      noise_val = np.random.normal(0, 1, (5000, 100))
+
+      labels_train = np.zeros(55000).reshape(-1, 1)
+      labels_test = np.zeros(10000).reshape(-1, 1)
+      labels_val = np.zeros(5000).reshape(-1, 1)
+
+      for i in range(10):
+        labels_train[i*5500:] = i
+        labels_test[i*1000:] = i
+        labels_val[i*500:] = i
+
+      train_data = self.generator.predict([noise_train, labels_train])
+      test_data = self.generator.predict([noise_test, labels_test])
+      val_data = self.generator.predict([noise_val, labels_val])
+
+      labels_train = keras.utils.to_categorical(labels_train, 10)
+      labels_test = keras.utils.to_categorical(labels_test, 10)
+      labels_val = keras.utils.to_categorical(labels_val, 10)
+
+      return train_data, test_data, val_data, labels_train, labels_test, labels_val
+
+'''
+if __name__ == '__main__':
+    cgan = CDCGAN()
+    cgan.train(epochs=70, batch_size=32, sample_interval=200)
+    train, test, tr_labels, te_labels = cgan.generate_data()
+    print(train.shape, test.shape)
+'''