aboutsummaryrefslogtreecommitdiff
path: root/cgan.py
blob: 64062445598eed846b072cc5405bad3496f227bb (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
from __future__ import print_function, division
import tensorflow.keras as keras
import tensorflow as tf
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
from IPython.display import clear_output
from tqdm import tqdm

import numpy as np

class CGAN():
    def __init__(self, dense_layers = 3):
        # 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
        self.dense_layers = dense_layers

        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()

        for i in range(self.dense_layers):
            output_size = 2**(8+i)
            model.add(Dense(output_size, input_dim=self.latent_dim))
            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, 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 = CGAN(dense_layers=1)
    cgan.train(epochs=7000, batch_size=32, sample_interval=200)
    train, test, tr_labels, te_labels = cgan.generate_data()
    print(train.shape, test.shape)
'''