diff options
| -rw-r--r-- | cgan.py | 214 | ||||
| -rw-r--r-- | dcgan.py | 186 |
2 files changed, 400 insertions, 0 deletions
@@ -0,0 +1,214 @@ +from __future__ import print_function, division + +from keras.datasets import mnist +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 + +import numpy as np + +class CGAN(): + 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): + + model = Sequential() + + model.add(Dense(256, input_dim=self.latent_dim)) + model.add(LeakyReLU(alpha=0.2)) + model.add(BatchNormalization(momentum=0.8)) + model.add(Dense(512)) + model.add(LeakyReLU(alpha=0.2)) + model.add(BatchNormalization(momentum=0.8)) + model.add(Dense(1024)) + model.add(LeakyReLU(alpha=0.2)) + model.add(BatchNormalization(momentum=0.8)) + model.add(Dense(np.prod(self.img_shape), activation='tanh')) + model.add(Reshape(self.img_shape)) + + #model.summary() + + noise = Input(shape=(self.latent_dim,)) + label = Input(shape=(1,), dtype='int32') + label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label)) + + model_input = multiply([noise, label_embedding]) + img = model(model_input) + + return Model([noise, label], img) + + def build_discriminator(self): + + model = Sequential() + + model.add(Dense(512, input_dim=np.prod(self.img_shape))) + model.add(LeakyReLU(alpha=0.2)) + model.add(Dense(512)) + model.add(LeakyReLU(alpha=0.2)) + model.add(Dropout(0.4)) + model.add(Dense(512)) + model.add(LeakyReLU(alpha=0.2)) + model.add(Dropout(0.4)) + model.add(Dense(1, activation='sigmoid')) + + #model.summary() + + img = Input(shape=self.img_shape) + label = Input(shape=(1,), dtype='int32') + + label_embedding = Flatten()(Embedding(self.num_classes, np.prod(self.img_shape))(label)) + flat_img = Flatten()(img) + + model_input = multiply([flat_img, label_embedding]) + + validity = model(model_input) + + return Model([img, label], validity) + + def train(self, epochs, batch_size=128, sample_interval=50, graph=False): + + # 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 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) + d_loss_fake = self.discriminator.train_on_batch([gen_imgs, labels], 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)) + if epoch % 500 == 0: + print(epoch) + 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) + dummy_labels = np.zeros(32).reshape(-1, 1) + + gen_imgs = self.generator.predict([noise, dummy_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, (60000, 100)) + noise_test = np.random.normal(0, 1, (10000, 100)) + + gen_train = np.zeros(60000).reshape(-1, 1) + gen_test = np.zeros(10000).reshape(-1, 1) + for i in range(10): + gen_train[i*600:] = i + gen_test[i*100:] = i + + return self.generator.predict([noise_train, gen_train]), self.generator.predict([noise_test, gen_test]), gen_train, gen_test + + +''' +if __name__ == '__main__': + cgan = CGAN() + cgan.train(epochs=7000, batch_size=32, sample_interval=200) + train, test, tr_labels, te_labels = cgan.generate_data() + print(train.shape, test.shape) +'''
\ No newline at end of file diff --git a/dcgan.py b/dcgan.py new file mode 100644 index 0000000..b48e99f --- /dev/null +++ b/dcgan.py @@ -0,0 +1,186 @@ +from __future__ import print_function, division +from keras.datasets import mnist +from keras.layers import Input, Dense, Reshape, Flatten, Dropout +from keras.layers import BatchNormalization, Activation, 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 +import matplotlib.gridspec as gridspec + +import sys + +import numpy as np + +class DCGAN(): + 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.latent_dim = 100 + + optimizer = Adam(0.002, 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 as input and generates imgs + z = Input(shape=(self.latent_dim,)) + img = self.generator(z) + + # 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) + + # The combined model (stacked generator and discriminator) + # Trains the generator to fool the discriminator + self.combined = Model(z, valid) + self.combined.compile(loss='binary_crossentropy', optimizer=optimizer) + + def build_generator(self): + + model = Sequential() + + model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim)) + model.add(Reshape((7, 7, 128))) + model.add(UpSampling2D()) + model.add(Conv2D(128, kernel_size=3, padding="same")) + model.add(BatchNormalization()) + model.add(Activation("relu")) + model.add(UpSampling2D()) + model.add(Conv2D(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(Activation("tanh")) + + #model.summary() + + noise = Input(shape=(self.latent_dim,)) + img = model(noise) + + return Model(noise, img) + + def build_discriminator(self): + + model = Sequential() + + model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=self.img_shape, 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() + + img = Input(shape=self.img_shape) + validity = model(img) + + return Model(img, validity) + + def train(self, epochs, batch_size=128, save_interval=50): + + # Load the dataset + (X_train, _), (_, _) = mnist.load_data() + + # Rescale -1 to 1 + X_train = X_train / 127.5 - 1. + X_train = np.expand_dims(X_train, axis=3) + + # 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 range(epochs): + + # --------------------- + # Train Discriminator + # --------------------- + + # Select a random half of images + idx = np.random.randint(0, X_train.shape[0], batch_size) + imgs = X_train[idx] + + # Sample noise and generate a batch of new images + noise = np.random.normal(0, 1, (batch_size, self.latent_dim)) + gen_imgs = self.generator.predict(noise) + + # Train the discriminator (real classified as ones and generated as zeros) + d_loss_real = self.discriminator.train_on_batch(imgs, valid) + d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake) + d_loss = 0.5 * np.add(d_loss_real, d_loss_fake) + + # --------------------- + # Train Generator + # --------------------- + + # Train the generator (wants discriminator to mistake images as real) + g_loss = self.combined.train_on_batch(noise, valid) + + # Plot the progress + #print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss)) + if epoch % 500 == 0: + print(epoch) + loss[0][epoch] = d_loss[0] + loss[1][epoch] = g_loss + # If at save interval => save generated image samples + if epoch % save_interval == 0: + self.save_imgs(epoch) + 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 save_imgs(self, epoch): + r, c = 10, 10 + noise = np.random.normal(0, 1, (r * c, self.latent_dim)) + gen_imgs = self.generator.predict(noise) + + # Rescale images 0 - 1 + gen_imgs = 0.5 * gen_imgs + 0.5 + + fig, axs = plt.subplots(r, c) + gs = gridspec.GridSpec(r, c) + gs.update(wspace=0.05, hspace=0.05) + 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].axis('off') + cnt += 1 + fig.savefig("images/mnist_%d.png" % epoch) + plt.close() + +''' +if __name__ == '__main__': + dcgan = DCGAN() + dcgan.train(epochs=4000, batch_size=32, save_interval=50) +'''
\ No newline at end of file |