def cnn1(time_periods,
input_shape,
number_of_sensors,
number_of_classes,
dropout_rate=0.5,
optimizer='adam',
activation='relu',
weight_constraint=None,
init_mode='glorot_uniform'):
model = tf.keras.Sequential()
model.add(
tf.keras.layers.Reshape((time_periods, number_of_sensors),
input_shape=(input_shape, )))
model.add(
tf.keras.layers.Conv1D(10,
10,
input_shape=(time_periods, number_of_sensors),
activation=activation,
kernel_constraint=maxnorm(weight_constraint),
kernel_initializer=init_mode))
model.add(
tf.keras.layers.Conv1D(10,
10,
activation=activation,
kernel_constraint=maxnorm(weight_constraint),
kernel_initializer=init_mode))
model.add(tf.keras.layers.MaxPooling1D(4))
model.add(
tf.keras.layers.Conv1D(16,
10,
activation=activation,
kernel_constraint=maxnorm(weight_constraint),
kernel_initializer=init_mode))
model.add(
tf.keras.layers.Conv1D(16,
10,
activation=activation,
kernel_constraint=maxnorm(weight_constraint),
kernel_initializer=init_mode))
model.add(tf.keras.layers.GlobalAveragePooling1D())
model.add(tf.keras.layers.Dropout(dropout_rate))
model.add(tf.keras.layers.Dense(number_of_classes, activation='softmax'))
print(model.summary())
model.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['acc', 'mse'])
return model
def create_model(epochs=25):
model = Sequential()
model.add(
Conv2D(32, (3, 3),
input_shape=(3, 32, 32),
padding='same',
activation='relu',
kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(
Conv2D(32, (3, 3),
activation='relu',
padding='same',
kernel_constraint=maxnorm(3)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(
Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(
Conv2D(64, (3, 3),
activation='relu',
padding='same',
kernel_constraint=maxnorm(3)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(
Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(
Conv2D(128, (3, 3),
activation='relu',
padding='same',
kernel_constraint=maxnorm(3)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dropout(0.2))
model.add(Dense(1024, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
lrate = 0.01
decay = lrate / epochs
sgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
return model
def seattle_model(input_width=32, input_height=32, feature_maps=32, feature_window_size=(5, 5), dropout1=0.2,
dense=128, dropout2=0.5, use_max_pooling=True, pool_size=(2, 2), optimizer='rmsprop'):
model = Sequential()
# - 20 feature maps (each feature map is a reduced-size convolution that detects a different feature)
# - 3 pixel square window
model.add(Conv2D(feature_maps,
feature_window_size,
input_shape=(input_width, input_height, 6),
padding='same',
data_format='channels_last',
activation='relu'))
# - 40 feature maps (add more features)
# - 3 pixel square window
model.add(Conv2D(feature_maps,
feature_window_size,
padding='same',
data_format='channels_last',
activation='relu'))
# Pooling layer
if use_max_pooling:
model.add(MaxPooling2D(pool_size=pool_size,
data_format='channels_last'))
else:
model.add(AveragePooling2D(pool_size=pool_size,
data_format='channels_last'))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128,
activation='relu',
kernel_constraint=maxnorm(3)))
# Dropout set to 50%.
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='categorical_crossentropy',
metrics=['binary_accuracy'],
optimizer='rmsprop')
return model
def design_dnn(nb_features,
input_shape,
nb_levels,
conv_size,
nb_labels,
feat_mult=1,
pool_size=2,
padding='same',
activation='elu',
final_layer='dense-sigmoid',
conv_dropout=0,
conv_maxnorm=0,
nb_input_features=1,
batch_norm=False,
name=None,
prefix=None,
use_strided_convolution_maxpool=True,
nb_conv_per_level=2):
"""
"deep" cnn with dense or global max pooling layer @ end...
Could use sequential...
"""
def _global_max_nd(xtens):
ytens = K.batch_flatten(xtens)
return K.max(ytens, 1, keepdims=True)
model_name = name
if model_name is None:
model_name = 'model_1'
if prefix is None:
prefix = model_name
ndims = len(input_shape)
input_shape = tuple(input_shape)
convL = getattr(KL, 'Conv%dD' % ndims)
maxpool = KL.MaxPooling3D if len(input_shape) == 3 else KL.MaxPooling2D
if isinstance(pool_size, int):
pool_size = (pool_size, ) * ndims
# kwargs for the convolution layer
conv_kwargs = {'padding': padding, 'activation': activation}
if conv_maxnorm > 0:
conv_kwargs['kernel_constraint'] = maxnorm(conv_maxnorm)
# initialize a dictionary
enc_tensors = {}
# first layer: input
name = '%s_input' % prefix
enc_tensors[name] = KL.Input(shape=input_shape + (nb_input_features, ),
name=name)
last_tensor = enc_tensors[name]
# down arm:
# add nb_levels of conv + ReLu + conv + ReLu. Pool after each of first nb_levels - 1 layers
for level in range(nb_levels):
for conv in range(nb_conv_per_level):
if conv_dropout > 0:
name = '%s_dropout_%d_%d' % (prefix, level, conv)
enc_tensors[name] = KL.Dropout(conv_dropout)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_conv_%d_%d' % (prefix, level, conv)
nb_lvl_feats = np.round(nb_features * feat_mult**level).astype(int)
enc_tensors[name] = convL(nb_lvl_feats,
conv_size,
**conv_kwargs,
name=name)(last_tensor)
last_tensor = enc_tensors[name]
# max pool
if use_strided_convolution_maxpool:
name = '%s_strided_conv_%d' % (prefix, level)
enc_tensors[name] = convL(nb_lvl_feats,
pool_size,
**conv_kwargs,
name=name)(last_tensor)
last_tensor = enc_tensors[name]
else:
name = '%s_maxpool_%d' % (prefix, level)
enc_tensors[name] = maxpool(pool_size=pool_size,
name=name,
padding=padding)(last_tensor)
last_tensor = enc_tensors[name]
# dense layer
if final_layer == 'dense-sigmoid':
name = "%s_flatten" % prefix
enc_tensors[name] = KL.Flatten(name=name)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_dense' % prefix
enc_tensors[name] = KL.Dense(1, name=name,
activation="sigmoid")(last_tensor)
elif final_layer == 'dense-tanh':
name = "%s_flatten" % prefix
enc_tensors[name] = KL.Flatten(name=name)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_dense' % prefix
enc_tensors[name] = KL.Dense(1, name=name)(last_tensor)
last_tensor = enc_tensors[name]
# Omittting BatchNorm for now, it seems to have a cpu vs gpu problem
# https://github.com/tensorflow/tensorflow/pull/8906
# https://github.com/fchollet/keras/issues/5802
# name = '%s_%s_bn' % prefix
# enc_tensors[name] = KL.BatchNormalization(axis=batch_norm, name=name)(last_tensor)
# last_tensor = enc_tensors[name]
name = '%s_%s_tanh' % prefix
enc_tensors[name] = KL.Activation(activation="tanh",
name=name)(last_tensor)
elif final_layer == 'dense-softmax':
name = "%s_flatten" % prefix
enc_tensors[name] = KL.Flatten(name=name)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_dense' % prefix
enc_tensors[name] = KL.Dense(nb_labels,
name=name,
activation="softmax")(last_tensor)
# global max pooling layer
elif final_layer == 'myglobalmaxpooling':
name = '%s_batch_norm' % prefix
enc_tensors[name] = KL.BatchNormalization(axis=batch_norm,
name=name)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_global_max_pool' % prefix
enc_tensors[name] = KL.Lambda(_global_max_nd, name=name)(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_global_max_pool_reshape' % prefix
enc_tensors[name] = KL.Reshape((1, 1), name=name)(last_tensor)
last_tensor = enc_tensors[name]
# cannot do activation in lambda layer. Could code inside, but will do extra lyaer
name = '%s_global_max_pool_sigmoid' % prefix
enc_tensors[name] = KL.Conv1D(1,
1,
name=name,
activation="sigmoid",
use_bias=True)(last_tensor)
elif final_layer == 'globalmaxpooling':
name = '%s_conv_to_featmaps' % prefix
enc_tensors[name] = KL.Conv3D(2, 1, name=name,
activation="relu")(last_tensor)
last_tensor = enc_tensors[name]
name = '%s_global_max_pool' % prefix
enc_tensors[name] = KL.GlobalMaxPooling3D(name=name)(last_tensor)
last_tensor = enc_tensors[name]
# cannot do activation in lambda layer. Could code inside, but will do extra lyaer
name = '%s_global_max_pool_softmax' % prefix
enc_tensors[name] = KL.Activation('softmax', name=name)(last_tensor)
last_tensor = enc_tensors[name]
# create the model
model = Model(inputs=[enc_tensors['%s_input' % prefix]],
outputs=[last_tensor],
name=model_name)
return model
def create_model(input_dim):
model = tf.keras.models.Sequential([
Conv2D(16, (3, 3),
activation="relu",
padding="same",
input_shape=input_dim),
Dropout(0.2),
BatchNormalization(),
Conv2D(32, (3, 3), activation="relu", padding="same"),
MaxPooling2D((2, 2)),
Activation('relu'),
Dropout(0.2),
BatchNormalization(),
Conv2D(64, (3, 3), activation="relu", padding="same"),
Dropout(0.2),
BatchNormalization(),
Conv2D(128, (3, 3), activation="relu", padding="same"),
MaxPooling2D((2, 2)),
Activation('relu'),
Dropout(0.2),
BatchNormalization(),
Conv2D(256, (3, 3), activation="relu", padding="same"),
Dropout(0.2),
BatchNormalization(),
Conv2D(512, (3, 3), activation="relu", padding="same"),
Dropout(0.2),
BatchNormalization(),
Conv2D(1024, (3, 3), activation="relu", padding="same"),
Dropout(0.2),
BatchNormalization(),
Flatten(),
Dropout(0.2),
Dense(2048,
activation="relu",
bias_regularizer=tf.keras.regularizers.L1L2(l1=0.01, l2=0.001),
kernel_constraint=maxnorm(3)),
Dropout(0.2),
BatchNormalization(),
Dense(1024,
activation="relu",
bias_regularizer=tf.keras.regularizers.L1L2(l1=0.01, l2=0.001),
kernel_constraint=maxnorm(3)),
Dropout(0.2),
BatchNormalization(),
Dense(512,
activation="relu",
bias_regularizer=tf.keras.regularizers.L1L2(l1=0.01, l2=0.001),
kernel_constraint=maxnorm(3)),
Dropout(0.2),
BatchNormalization(),
Dense(256,
activation="relu",
bias_regularizer=tf.keras.regularizers.L1L2(l1=0.01, l2=0.001),
kernel_constraint=maxnorm(3)),
Dropout(0.2),
BatchNormalization(),
Dense(128,
activation="relu",
bias_regularizer=tf.keras.regularizers.L1L2(l1=0.01, l2=0.001),
kernel_constraint=maxnorm(3)),
Dropout(0.2),
BatchNormalization(),
Dense(10, activation="softmax")
])
model.compile(
optimizer="adam",
loss="categorical_crossentropy",
metrics=["accuracy"],
)
return model
X = np.asarray(data_frame_for_tf) y = np.asarray(special_class) import tensorflow.python.keras from tensorflow.python.keras import Sequential from tensorflow.python.keras.layers import InputLayer from tensorflow.python.keras.layers import Dense from tensorflow.python.keras.layers import Dropout from tensorflow.python.keras.constraints import maxnorm from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size= 0.2, random_state= 1234) model = Sequential() model.add(Dense(1024, input_dim=18098, activation='relu', kernel_constraint=maxnorm(3))) model.add(Dropout(rate=0.2)) model.add(Dense(512, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(256, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(128, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(64, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(32, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(16, activation='relu', kernel_constraint=maxnorm(5))) model.add(Dropout(rate=0.2)) model.add(Dense(1, activation='sigmoid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Conv2D(128, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
# Flatting
model.add(Flatten())
model.add(Dropout(0.2))
# Classification
model.add(Dense(256, kernel_constraint=maxnorm(3)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(128, kernel_constraint=maxnorm(3)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(class_num))
model.add(Activation('softmax'))
# Set the epochs and optimizer
epochs = 25
optimizer = 'adam'