diff options
-rwxr-xr-x | cdcgan.py | 27 | ||||
-rw-r--r-- | dcgan.py | 5 | ||||
-rwxr-xr-x | ncdcgan.py | 265 |
3 files changed, 280 insertions, 17 deletions
@@ -7,7 +7,7 @@ from keras.datasets import mnist 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 +from keras.layers import UpSampling2D, Conv2D, Conv2DTranspose from keras.models import Sequential, Model from keras.optimizers import Adam @@ -65,25 +65,22 @@ class CDCGAN(): model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim)) model.add(Reshape((7, 7, 128))) - model.add(UpSampling2D()) - for i in range(self.conv_layers): - model.add(Conv2D(128, kernel_size=3, padding="same")) - model.add(BatchNormalization()) - model.add(Activation("relu")) - - model.add(UpSampling2D()) + model.add(Conv2DTranspose(256, kernel_size=3, padding="same", strides=(2,2))) + model.add(BatchNormalization()) + model.add(Activation("relu")) - for i in range(self.conv_layers): - model.add(Conv2D(64, kernel_size=3, padding="same")) - model.add(BatchNormalization()) + model.add(Conv2DTranspose(128, kernel_size=3, padding="same", strides=(2,2))) + model.add(BatchNormalization()) + model.add(Activation("relu")) - model.add(Activation("relu")) + model.add(Conv2DTranspose(64, kernel_size=3, padding="same")) + model.add(BatchNormalization()) + model.add(Activation("relu")) - model.add(Conv2D(self.channels, kernel_size=3, padding="same")) + model.add(Conv2DTranspose(1, kernel_size=3, padding="same")) model.add(Activation("tanh")) - #model.summary() noise = Input(shape=(self.latent_dim,)) label = Input(shape=(1,), dtype='int32') @@ -91,6 +88,8 @@ class CDCGAN(): model_input = multiply([noise, label_embedding]) img = model(model_input) + #model.summary() + return Model([noise, label], img) def build_discriminator(self): @@ -1,4 +1,5 @@ from __future__ import print_function, division +import tensorflow.keras as keras from keras.datasets import mnist from keras.layers import Input, Dense, Reshape, Flatten, Dropout from keras.layers import BatchNormalization, Activation, ZeroPadding2D @@ -76,7 +77,7 @@ class DCGAN(): model.add(Conv2D(self.channels, kernel_size=3, padding="same")) model.add(Activation("tanh")) - #model.summary() + model.summary() noise = Input(shape=(self.latent_dim,)) img = model(noise) @@ -191,8 +192,6 @@ class DCGAN(): fig.savefig("images/mnist_%d.png" % epoch) plt.close() -''' if __name__ == '__main__': dcgan = DCGAN() dcgan.train(epochs=4000, batch_size=32, save_interval=50) -''' diff --git a/ncdcgan.py b/ncdcgan.py new file mode 100755 index 0000000..ccb99d3 --- /dev/null +++ b/ncdcgan.py @@ -0,0 +1,265 @@ +from __future__ import print_function, division +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 BatchNormalization, Embedding, Activation, ZeroPadding2D +from keras.layers import LeakyReLU +from keras.layers import UpSampling2D, Conv2D, Conv2DTranspose +from keras.models import Sequential, Model +from keras.optimizers import Adam + +import matplotlib.pyplot as plt +import matplotlib.gridspec as gridspec + +from tqdm import tqdm + +import sys + +import numpy as np + +class nCDCGAN(): + def __init__(self, conv_layers = 1, num_classes = 10): + # Input shape + self.num_classes = num_classes + self.img_rows = 28 + self.img_cols = 28 + self.channels = 1 + self.img_shape = (self.img_rows, self.img_cols, self.channels) + self.latent_dim = 100 + self.conv_layers = conv_layers + + 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(ph_img, label) + self.discriminator.compile(loss='binary_crossentropy', + optimizer=optimizer, + metrics=['accuracy']) + + img = self.generator([noise, label]) + + + + # For the combined model we will only train the generator + self.discriminator.trainable = False + + # The discriminator takes generated images as input and determines validity + 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, noise, 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) + + 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, 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) + + + 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 + + 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]) + + 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]) + + + 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 + + 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): + + # 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:-1] = i + labels_test[i*1000:-1] = i + labels_val[i*500:-1] = 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__': + cdcgan = nCDCGAN() + cdcgan.train(epochs=4000, batch_size=32) +''' |