-

Deep-Learning-with-Keras/Appendix/legacy.py

@@ -0,0 +1,59 @@
+"""
+Utility functions to avoid warnings while testing both Keras 1 and 2.
+"""
+import keras
+
+keras_2 = int(keras.__version__.split(".")[0]) > 1  # Keras > 1
+
+
+def fit_generator(model, generator, epochs, steps_per_epoch):
+    if keras_2:
+        model.fit_generator(generator, epochs=epochs, steps_per_epoch=steps_per_epoch)
+    else:
+        model.fit_generator(generator, nb_epoch=epochs, samples_per_epoch=steps_per_epoch)
+
+
+def fit(model, x, y, nb_epoch=10, *args, **kwargs):
+    if keras_2:
+        return model.fit(x, y, *args, epochs=nb_epoch, **kwargs)
+    else:
+        return model.fit(x, y, *args, nb_epoch=nb_epoch, **kwargs)
+
+
+def l1l2(l1=0, l2=0):
+    if keras_2:
+        return keras.regularizers.L1L2(l1, l2)
+    else:
+        return keras.regularizers.l1l2(l1, l2)
+
+
+def Dense(units, W_regularizer=None, W_initializer='glorot_uniform', **kwargs):
+    if keras_2:
+        return keras.layers.Dense(units, kernel_regularizer=W_regularizer, kernel_initializer=W_initializer, **kwargs)
+    else:
+        return keras.layers.Dense(units, W_regularizer=W_regularizer, init=W_initializer, **kwargs)
+
+
+def BatchNormalization(mode=0, **kwargs):
+    if keras_2:
+        return keras.layers.BatchNormalization(**kwargs)
+    else:
+        return keras.layers.BatchNormalization(mode=mode, **kwargs)
+
+
+def Convolution2D(units, w, h, W_regularizer=None, W_initializer='glorot_uniform', border_mode='same', **kwargs):
+    if keras_2:
+        return keras.layers.Convolution2D(units, (w, h), padding=border_mode, kernel_regularizer=W_regularizer,
+                                          kernel_initializer=W_initializer,
+                                          **kwargs)
+    else:
+        return keras.layers.Convolution2D(units, w, h, border_mode=border_mode, W_regularizer=W_regularizer,
+                                          init=W_initializer,
+                                          **kwargs)
+
+
+def AveragePooling2D(pool_size, border_mode='valid', **kwargs):
+    if keras_2:
+        return keras.layers.AveragePooling2D(pool_size=pool_size, padding=border_mode, **kwargs)
+    else:
+        return keras.layers.AveragePooling2D(pool_size=pool_size, border_mode=border_mode, **kwargs)

Deep-Learning-with-Keras/Chapter01/keras_MINST_V1.py

@@ -0,0 +1,61 @@
+from __future__ import print_function
+import numpy as np
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers.core import Dense, Activation
+from keras.optimizers import SGD
+from keras.utils import np_utils
+
+np.random.seed(1671)  # for reproducibility
+
+# network and training
+NB_EPOCH = 200
+BATCH_SIZE = 128
+VERBOSE = 1
+NB_CLASSES = 10   # number of outputs = number of digits
+OPTIMIZER = SGD() # SGD optimizer, explained later in this chapter
+N_HIDDEN = 128
+VALIDATION_SPLIT=0.2 # how much TRAIN is reserved for VALIDATION
+
+# data: shuffled and split between train and test sets
+#
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
+RESHAPED = 784
+#
+X_train = X_train.reshape(60000, RESHAPED)
+X_test = X_test.reshape(10000, RESHAPED)
+X_train = X_train.astype('float32')
+X_test = X_test.astype('float32')
+
+# normalize 
+#
+X_train /= 255
+X_test /= 255
+print(X_train.shape[0], 'train samples')
+print(X_test.shape[0], 'test samples')
+
+# convert class vectors to binary class matrices
+Y_train = np_utils.to_categorical(y_train, NB_CLASSES)
+Y_test = np_utils.to_categorical(y_test, NB_CLASSES)
+
+# 10 outputs
+# final stage is softmax
+
+model = Sequential()
+model.add(Dense(NB_CLASSES, input_shape=(RESHAPED,)))
+model.add(Activation('softmax'))
+
+model.summary()
+
+model.compile(loss='categorical_crossentropy',
+              optimizer=OPTIMIZER,
+              metrics=['accuracy'])
+
+history = model.fit(X_train, Y_train,
+                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
+                    verbose=VERBOSE, validation_split=VALIDATION_SPLIT)
+score = model.evaluate(X_test, Y_test, verbose=VERBOSE)
+print("\nTest score:", score[0])
+print('Test accuracy:', score[1])

Deep-Learning-with-Keras/Chapter01/keras_MINST_V2.py

@@ -0,0 +1,64 @@
+from __future__ import print_function
+import numpy as np
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers.core import Dense, Activation
+from keras.optimizers import SGD
+from keras.utils import np_utils
+
+np.random.seed(1671)  # for reproducibility
+
+# network and training
+NB_EPOCH = 20
+BATCH_SIZE = 128
+VERBOSE = 1
+NB_CLASSES = 10   # number of outputs = number of digits
+OPTIMIZER = SGD() # optimizer, explained later in this chapter
+N_HIDDEN = 128
+VALIDATION_SPLIT=0.2 # how much TRAIN is reserved for VALIDATION
+
+# data: shuffled and split between train and test sets
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
+RESHAPED = 784
+#
+X_train = X_train.reshape(60000, RESHAPED)
+X_test = X_test.reshape(10000, RESHAPED)
+X_train = X_train.astype('float32')
+X_test = X_test.astype('float32')
+
+# normalize 
+X_train /= 255
+X_test /= 255
+print(X_train.shape[0], 'train samples')
+print(X_test.shape[0], 'test samples')
+
+# convert class vectors to binary class matrices
+Y_train = np_utils.to_categorical(y_train, NB_CLASSES)
+Y_test = np_utils.to_categorical(y_test, NB_CLASSES)
+
+# M_HIDDEN hidden layers
+# 10 outputs
+# final stage is softmax
+
+model = Sequential()
+model.add(Dense(N_HIDDEN, input_shape=(RESHAPED,)))
+model.add(Activation('relu'))
+model.add(Dense(N_HIDDEN))
+model.add(Activation('relu'))
+model.add(Dense(NB_CLASSES))
+model.add(Activation('softmax'))
+model.summary()
+
+model.compile(loss='categorical_crossentropy',
+              optimizer=OPTIMIZER,
+              metrics=['accuracy'])
+
+history = model.fit(X_train, Y_train,
+                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
+                    verbose=VERBOSE, validation_split=VALIDATION_SPLIT)
+
+score = model.evaluate(X_test, Y_test, verbose=VERBOSE)
+print("\nTest score:", score[0])
+print('Test accuracy:', score[1])

Deep-Learning-with-Keras/Chapter01/keras_MINST_V3.py

@@ -0,0 +1,88 @@
+from __future__ import print_function
+import numpy as np
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers.core import Dense, Dropout, Activation
+from keras.optimizers import SGD
+from keras.utils import np_utils
+
+import matplotlib.pyplot as plt
+
+np.random.seed(1671)  # for reproducibility
+
+# network and training
+NB_EPOCH = 250
+BATCH_SIZE = 128
+VERBOSE = 1
+NB_CLASSES = 10   # number of outputs = number of digits
+OPTIMIZER = SGD() # optimizer, explained later in this chapter
+N_HIDDEN = 128
+VALIDATION_SPLIT=0.2 # how much TRAIN is reserved for VALIDATION
+DROPOUT = 0.3
+
+# data: shuffled and split between train and test sets
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
+RESHAPED = 784
+#
+X_train = X_train.reshape(60000, RESHAPED)
+X_test = X_test.reshape(10000, RESHAPED)
+X_train = X_train.astype('float32')
+X_test = X_test.astype('float32')
+
+# normalize 
+X_train /= 255
+X_test /= 255
+print(X_train.shape[0], 'train samples')
+print(X_test.shape[0], 'test samples')
+
+# convert class vectors to binary class matrices
+Y_train = np_utils.to_categorical(y_train, NB_CLASSES)
+Y_test = np_utils.to_categorical(y_test, NB_CLASSES)
+
+# M_HIDDEN hidden layers
+# 10 outputs
+# final stage is softmax
+
+model = Sequential()
+model.add(Dense(N_HIDDEN, input_shape=(RESHAPED,)))
+model.add(Activation('relu'))
+model.add(Dropout(DROPOUT))
+model.add(Dense(N_HIDDEN))
+model.add(Activation('relu'))
+model.add(Dropout(DROPOUT))
+model.add(Dense(NB_CLASSES))
+model.add(Activation('softmax'))
+model.summary()
+
+model.compile(loss='categorical_crossentropy',
+              optimizer=OPTIMIZER,
+              metrics=['accuracy'])
+
+history = model.fit(X_train, Y_train,
+                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
+                    verbose=VERBOSE, validation_split=VALIDATION_SPLIT)
+
+score = model.evaluate(X_test, Y_test, verbose=VERBOSE)
+print("\nTest score:", score[0])
+print('Test accuracy:', score[1])
+
+# list all data in history
+print(history.history.keys())
+# summarize history for accuracy
+plt.plot(history.history['acc'])
+plt.plot(history.history['val_acc'])
+plt.title('model accuracy')
+plt.ylabel('accuracy')
+plt.xlabel('epoch')
+plt.legend(['train', 'test'], loc='upper left')
+plt.show()
+# summarize history for loss
+plt.plot(history.history['loss'])
+plt.plot(history.history['val_loss'])
+plt.title('model loss')
+plt.ylabel('loss')
+plt.xlabel('epoch')
+plt.legend(['train', 'test'], loc='upper left')
+plt.show()

Deep-Learning-with-Keras/Chapter01/keras_MINST_V4.py

@@ -0,0 +1,88 @@
+from __future__ import print_function
+import numpy as np
+from keras.datasets import mnist
+from keras.models import Sequential
+from keras.layers.core import Dense, Dropout, Activation
+from keras.optimizers import RMSprop
+from keras.utils import np_utils
+
+import matplotlib.pyplot as plt
+
+np.random.seed(1671)  # for reproducibility
+
+# network and training
+NB_EPOCH = 20
+BATCH_SIZE = 128
+VERBOSE = 1
+NB_CLASSES = 10   # number of outputs = number of digits
+OPTIMIZER = RMSprop() # optimizer, explainedin this chapter
+N_HIDDEN = 128
+VALIDATION_SPLIT=0.2 # how much TRAIN is reserved for VALIDATION
+DROPOUT = 0.3
+
+# data: shuffled and split between train and test sets
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
+RESHAPED = 784
+#
+X_train = X_train.reshape(60000, RESHAPED)
+X_test = X_test.reshape(10000, RESHAPED)
+X_train = X_train.astype('float32')
+X_test = X_test.astype('float32')
+
+# normalize 
+X_train /= 255
+X_test /= 255
+print(X_train.shape[0], 'train samples')
+print(X_test.shape[0], 'test samples')
+
+# convert class vectors to binary class matrices
+Y_train = np_utils.to_categorical(y_train, NB_CLASSES)
+Y_test = np_utils.to_categorical(y_test, NB_CLASSES)
+
+# M_HIDDEN hidden layers
+# 10 outputs
+# final stage is softmax
+
+model = Sequential()
+model.add(Dense(N_HIDDEN, input_shape=(RESHAPED,)))
+model.add(Activation('relu'))
+model.add(Dropout(DROPOUT))
+model.add(Dense(N_HIDDEN))
+model.add(Activation('relu'))
+model.add(Dropout(DROPOUT))
+model.add(Dense(NB_CLASSES))
+model.add(Activation('softmax'))
+model.summary()
+
+model.compile(loss='categorical_crossentropy',
+              optimizer=OPTIMIZER,
+              metrics=['accuracy'])
+
+history = model.fit(X_train, Y_train,
+                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
+                    verbose=VERBOSE, validation_split=VALIDATION_SPLIT)
+
+score = model.evaluate(X_test, Y_test, verbose=VERBOSE)
+print("\nTest score:", score[0])
+print('Test accuracy:', score[1])
+
+# list all data in history
+print(history.history.keys())
+# summarize history for accuracy
+plt.plot(history.history['acc'])
+plt.plot(history.history['val_acc'])
+plt.title('model accuracy')
+plt.ylabel('accuracy')
+plt.xlabel('epoch')
+plt.legend(['train', 'test'], loc='upper left')
+plt.show()
+# summarize history for loss
+plt.plot(history.history['loss'])
+plt.plot(history.history['val_loss'])
+plt.title('model loss')
+plt.ylabel('loss')
+plt.xlabel('epoch')
+plt.legend(['train', 'test'], loc='upper left')
+plt.show()

Deep-Learning-with-Keras/Chapter02/cifar10_architecture.json

@@ -0,0 +1 @@
+{"class_name": "Sequential", "keras_version": "1.1.1", "config": [{"class_name": "Convolution2D", "config": {"b_regularizer": null, "W_constraint": null, "b_constraint": null, "name": "convolution2d_1", "activity_regularizer": null, "trainable": true, "dim_ordering": "th", "nb_col": 3, "subsample": [1, 1], "init": "glorot_uniform", "bias": true, "nb_filter": 32, "input_dtype": "float32", "border_mode": "same", "batch_input_shape": [null, 3, 32, 32], "W_regularizer": null, "activation": "linear", "nb_row": 3}}, {"class_name": "Activation", "config": {"activation": "relu", "trainable": true, "name": "activation_1"}}, {"class_name": "Convolution2D", "config": {"W_constraint": null, "b_constraint": null, "name": "convolution2d_2", "activity_regularizer": null, "trainable": true, "dim_ordering": "th", "nb_col": 3, "subsample": [1, 1], "init": "glorot_uniform", "bias": true, "nb_filter": 32, "border_mode": "same", "b_regularizer": null, "W_regularizer": null, "activation": "linear", "nb_row": 3}}, {"class_name": "Activation", "config": {"activation": "relu", "trainable": true, "name": "activation_2"}}, {"class_name": "MaxPooling2D", "config": {"name": "maxpooling2d_1", "trainable": true, "dim_ordering": "th", "pool_size": [2, 2], "strides": [2, 2], "border_mode": "valid"}}, {"class_name": "Dropout", "config": {"p": 0.25, "trainable": true, "name": "dropout_1"}}, {"class_name": "Convolution2D", "config": {"W_constraint": null, "b_constraint": null, "name": "convolution2d_3", "activity_regularizer": null, "trainable": true, "dim_ordering": "th", "nb_col": 3, "subsample": [1, 1], "init": "glorot_uniform", "bias": true, "nb_filter": 64, "border_mode": "same", "b_regularizer": null, "W_regularizer": null, "activation": "linear", "nb_row": 3}}, {"class_name": "Activation", "config": {"activation": "relu", "trainable": true, "name": "activation_3"}}, {"class_name": "Convolution2D", "config": {"W_constraint": null, "b_constraint": null, "name": "convolution2d_4", "activity_regularizer": null, "trainable": true, "dim_ordering": "th", "nb_col": 3, "subsample": [1, 1], "init": "glorot_uniform", "bias": true, "nb_filter": 64, "border_mode": "valid", "b_regularizer": null, "W_regularizer": null, "activation": "linear", "nb_row": 3}}, {"class_name": "Activation", "config": {"activation": "relu", "trainable": true, "name": "activation_4"}}, {"class_name": "MaxPooling2D", "config": {"name": "maxpooling2d_2", "trainable": true, "dim_ordering": "th", "pool_size": [2, 2], "strides": [2, 2], "border_mode": "valid"}}, {"class_name": "Dropout", "config": {"p": 0.25, "trainable": true, "name": "dropout_2"}}, {"class_name": "Flatten", "config": {"trainable": true, "name": "flatten_1"}}, {"class_name": "Dense", "config": {"W_constraint": null, "b_constraint": null, "name": "dense_1", "activity_regularizer": null, "trainable": true, "init": "glorot_uniform", "bias": true, "input_dim": null, "b_regularizer": null, "W_regularizer": null, "activation": "linear", "output_dim": 512}}, {"class_name": "Activation", "config": {"activation": "relu", "trainable": true, "name": "activation_5"}}, {"class_name": "Dropout", "config": {"p": 0.5, "trainable": true, "name": "dropout_3"}}, {"class_name": "Dense", "config": {"W_constraint": null, "b_constraint": null, "name": "dense_2", "activity_regularizer": null, "trainable": true, "init": "glorot_uniform", "bias": true, "input_dim": null, "b_regularizer": null, "W_regularizer": null, "activation": "linear", "output_dim": 10}}, {"class_name": "Activation", "config": {"activation": "softmax", "trainable": true, "name": "activation_6"}}]}