Replace literal constant 10 with variable num_classes in example/ (k…

…eras-team#8041)

* Replace literal constant 10 with variable num_classes

* Fix PEP8 errors

examples/antirectifier.py

@@ -88,7 +88,7 @@ def call(self, inputs):
 model.add(layers.Dense(256))
 model.add(Antirectifier())
 model.add(layers.Dropout(0.1))
-model.add(layers.Dense(10))
+model.add(layers.Dense(num_classes))
 model.add(layers.Activation('softmax'))
 
 # compile the model

examples/mnist_acgan.py

@@ -46,6 +46,8 @@
 
 K.set_image_data_format('channels_first')
 
+num_classes = 10
+
 
 def build_generator(latent_size):
     # we will map a pair of (z, L), where z is a latent vector and L is a
@@ -79,8 +81,7 @@ def build_generator(latent_size):
     # this will be our label
     image_class = Input(shape=(1,), dtype='int32')
 
-    # 10 classes in MNIST
-    cls = Flatten()(Embedding(10, latent_size,
+    cls = Flatten()(Embedding(num_classes, latent_size,
                               embeddings_initializer='glorot_normal')(image_class))
 
     # hadamard product between z-space and a class conditional embedding
@@ -124,7 +125,7 @@ def build_discriminator():
     # (name=auxiliary) is the class that the discriminator thinks the image
     # belongs to.
     fake = Dense(1, activation='sigmoid', name='generation')(features)
-    aux = Dense(10, activation='softmax', name='auxiliary')(features)
+    aux = Dense(num_classes, activation='softmax', name='auxiliary')(features)
 
     return Model(image, [fake, aux])
 
@@ -200,7 +201,7 @@ def build_discriminator():
             label_batch = y_train[index * batch_size:(index + 1) * batch_size]
 
             # sample some labels from p_c
-            sampled_labels = np.random.randint(0, 10, batch_size)
+            sampled_labels = np.random.randint(0, num_classes, batch_size)
 
             # generate a batch of fake images, using the generated labels as a
             # conditioner. We reshape the sampled labels to be
@@ -220,7 +221,7 @@ def build_discriminator():
             # the generator optimize over an identical number of images as the
             # discriminator
             noise = np.random.uniform(-1, 1, (2 * batch_size, latent_size))
-            sampled_labels = np.random.randint(0, 10, 2 * batch_size)
+            sampled_labels = np.random.randint(0, num_classes, 2 * batch_size)
 
             # we want to train the generator to trick the discriminator
             # For the generator, we want all the {fake, not-fake} labels to say
@@ -239,7 +240,7 @@ def build_discriminator():
         noise = np.random.uniform(-1, 1, (num_test, latent_size))
 
         # sample some labels from p_c and generate images from them
-        sampled_labels = np.random.randint(0, 10, num_test)
+        sampled_labels = np.random.randint(0, num_classes, num_test)
         generated_images = generator.predict(
             [noise, sampled_labels.reshape((-1, 1))], verbose=False)
 
@@ -255,7 +256,7 @@ def build_discriminator():
 
         # make new noise
         noise = np.random.uniform(-1, 1, (2 * num_test, latent_size))
-        sampled_labels = np.random.randint(0, 10, 2 * num_test)
+        sampled_labels = np.random.randint(0, num_classes, 2 * num_test)
 
         trick = np.ones(2 * num_test)
 
@@ -296,7 +297,7 @@ def build_discriminator():
         noise = np.random.uniform(-1, 1, (100, latent_size))
 
         sampled_labels = np.array([
-            [i] * 10 for i in range(10)
+            [i] * num_classes for i in range(num_classes)
         ]).reshape(-1, 1)
 
         # get a batch to display
@@ -305,7 +306,7 @@ def build_discriminator():
 
         # arrange them into a grid
         img = (np.concatenate([r.reshape(-1, 28)
-                               for r in np.split(generated_images, 10)
+                               for r in np.split(generated_images, num_classes)
                                ], axis=-1) * 127.5 + 127.5).astype(np.uint8)
 
         Image.fromarray(img).save(

examples/mnist_mlp.py

@@ -13,7 +13,6 @@
 from keras.layers import Dense, Dropout
 from keras.optimizers import RMSprop
 
-
 batch_size = 128
 num_classes = 10
 epochs = 20
@@ -39,7 +38,7 @@
 model.add(Dropout(0.2))
 model.add(Dense(512, activation='relu'))
 model.add(Dropout(0.2))
-model.add(Dense(10, activation='softmax'))
+model.add(Dense(num_classes, activation='softmax'))
 
 model.summary()
 

examples/mnist_siamese_graph.py

@@ -21,6 +21,8 @@
 from keras.optimizers import RMSprop
 from keras import backend as K
 
+num_classes = 10
+
 
 def euclidean_distance(vects):
     x, y = vects
@@ -47,13 +49,13 @@ def create_pairs(x, digit_indices):
     '''
     pairs = []
     labels = []
-    n = min([len(digit_indices[d]) for d in range(10)]) - 1
-    for d in range(10):
+    n = min([len(digit_indices[d]) for d in range(num_classes)]) - 1
+    for d in range(num_classes):
         for i in range(n):
             z1, z2 = digit_indices[d][i], digit_indices[d][i + 1]
             pairs += [[x[z1], x[z2]]]
-            inc = random.randrange(1, 10)
-            dn = (d + inc) % 10
+            inc = random.randrange(1, num_classes)
+            dn = (d + inc) % num_classes
             z1, z2 = digit_indices[d][i], digit_indices[dn][i]
             pairs += [[x[z1], x[z2]]]
             labels += [1, 0]
@@ -97,10 +99,10 @@ def accuracy(y_true, y_pred):
 epochs = 20
 
 # create training+test positive and negative pairs
-digit_indices = [np.where(y_train == i)[0] for i in range(10)]
+digit_indices = [np.where(y_train == i)[0] for i in range(num_classes)]
 tr_pairs, tr_y = create_pairs(x_train, digit_indices)
 
-digit_indices = [np.where(y_test == i)[0] for i in range(10)]
+digit_indices = [np.where(y_test == i)[0] for i in range(num_classes)]
 te_pairs, te_y = create_pairs(x_test, digit_indices)
 
 # network definition

examples/mnist_tfrecord.py

@@ -61,7 +61,7 @@ def cnn_layers(x_train_input):
     x = layers.Flatten()(x)
     x = layers.Dense(512, activation='relu')(x)
     x = layers.Dropout(0.5)(x)
-    x_train_out = layers.Dense(classes,
+    x_train_out = layers.Dense(num_classes,
                                activation='softmax',
                                name='x_train_out')(x)
     return x_train_out
@@ -72,7 +72,7 @@ def cnn_layers(x_train_input):
 batch_shape = (batch_size, 28, 28, 1)
 steps_per_epoch = 469
 epochs = 5
-classes = 10
+num_classes = 10
 
 # The capacity variable controls the maximum queue size
 # allowed when prefetching data for training.
@@ -106,7 +106,7 @@ def cnn_layers(x_train_input):
 x_train_batch = tf.reshape(x_train_batch, shape=batch_shape)
 
 y_train_batch = tf.cast(y_train_batch, tf.int32)
-y_train_batch = tf.one_hot(y_train_batch, classes)
+y_train_batch = tf.one_hot(y_train_batch, num_classes)
 
 x_batch_shape = x_train_batch.get_shape().as_list()
 y_batch_shape = y_train_batch.get_shape().as_list()
@@ -153,5 +153,5 @@ def cnn_layers(x_train_input):
 
 loss, acc = test_model.evaluate(x_test,
                                 keras.utils.to_categorical(y_test),
-                                classes)
+                                num_classes)
 print('\nTest accuracy: {0}'.format(acc))