From 03f2c41ac69084cde7a61eb04303078e3c4785a7 Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 20:03:09 +0000 Subject: Update cdcgan with *better* one --- cdcgan.py | 20 +++++++------------- dcgan.py | 5 ++--- 2 files changed, 9 insertions(+), 16 deletions(-) diff --git a/cdcgan.py b/cdcgan.py index 7b517ca..01368ac 100755 --- a/cdcgan.py +++ b/cdcgan.py @@ -65,22 +65,16 @@ 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()) - - for i in range(self.conv_layers): - model.add(Conv2D(64, kernel_size=3, padding="same")) - model.add(BatchNormalization()) + model.add(Conv2DTranspose(256, kernel_size=3, padding="same", strides=(2,2))) + model.add(BatchNormalization()) + model.add(Activation("relu")) - model.add(Activation("relu")) + model.add(Conv2DTranspose(128, kernel_size=3, padding="same", strides=(2,2))) + model.add(BatchNormalization()) + model.add(Activation("relu")) - model.add(Conv2D(self.channels, kernel_size=3, padding="same")) + model.add(Conv2DTranspose(64, kernel_size=3, padding="same")) model.add(Activation("tanh")) #model.summary() diff --git a/dcgan.py b/dcgan.py index 347f61e..719e096 100644 --- a/dcgan.py +++ b/dcgan.py @@ -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 @@ -75,7 +76,7 @@ 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) @@ -187,8 +188,6 @@ 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) -''' -- cgit v1.2.3 From 9b71f4e88cab0f1981dc0e2a846510894756ea8a Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 20:05:24 +0000 Subject: Add import --- dcgan.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dcgan.py b/dcgan.py index a362f69..f65f742 100644 --- a/dcgan.py +++ b/dcgan.py @@ -4,7 +4,7 @@ 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.layers.convolutional import UpSampling2D, Conv2D, Conv2DTranspose from keras.models import Sequential, Model from keras.optimizers import Adam -- cgit v1.2.3 From a5f79e9ad499681c77630f71d00c95715b5f6b9e Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 20:05:48 +0000 Subject: Revert "Add import" This reverts commit 9b71f4e88cab0f1981dc0e2a846510894756ea8a. --- dcgan.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dcgan.py b/dcgan.py index f65f742..a362f69 100644 --- a/dcgan.py +++ b/dcgan.py @@ -4,7 +4,7 @@ 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, Conv2DTranspose +from keras.layers.convolutional import UpSampling2D, Conv2D from keras.models import Sequential, Model from keras.optimizers import Adam -- cgit v1.2.3 From c73345e0d2f253faf55fe55280e34ebf801eb82f Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 20:06:08 +0000 Subject: Add import --- cdcgan.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cdcgan.py b/cdcgan.py index 895def2..f2122b8 100755 --- a/cdcgan.py +++ b/cdcgan.py @@ -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 -- cgit v1.2.3 From 0522b299f1e3771eb4529dbd61bf069338b27318 Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 20:11:48 +0000 Subject: Fix cdcgan --- cdcgan.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/cdcgan.py b/cdcgan.py index f2122b8..effc89b 100755 --- a/cdcgan.py +++ b/cdcgan.py @@ -75,9 +75,12 @@ class CDCGAN(): model.add(Activation("relu")) model.add(Conv2DTranspose(64, kernel_size=3, padding="same")) + model.add(BatchNormalization()) + model.add(Activation("relu")) + + 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') @@ -85,6 +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): -- cgit v1.2.3 From 99a56a37bb47bdc814d9433fe5208c39b3a45ee4 Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 21:09:06 +0000 Subject: Add ncdcgan --- ncdcgan.py | 258 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 258 insertions(+) create mode 100755 ncdcgan.py diff --git a/ncdcgan.py b/ncdcgan.py new file mode 100755 index 0000000..7aa7e83 --- /dev/null +++ b/ncdcgan.py @@ -0,0 +1,258 @@ +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) + + # 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() + + 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 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 = 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) + + model = Model(inputs=[noise, label], outputs=x) + + model.summary() + + return model + + def build_discriminator(self): + + model = Sequential() + + 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() + + 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, 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) +''' + -- cgit v1.2.3 From 7d27d947d20ef28d3959cd358569f27bd0310111 Mon Sep 17 00:00:00 2001 From: Vasil Zlatanov Date: Wed, 13 Mar 2019 21:28:37 +0000 Subject: Work ncdcgan --- ncdcgan.py | 153 ++++++++++++++++++++++++++++++++----------------------------- 1 file 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) ''' - -- cgit v1.2.3