def get_cnn_adv(input_data, num_labels):
model = Sequential()
div = 4
model.add(Conv2D(64, kernel_size=(input_data.shape[0] // div, 1), activation='relu', input_shape=input_data.shape))
model.add(Conv2D(128, kernel_size=(div, 8), activation='relu'))
model.add(Flatten())
model.add(Dense(500, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_labels, activation='softmax'))
opt = Adamax(learning_rate=KeyConstants.ELR)
model.compile(loss='categorical_crossentropy', opt=opt, metrics=['accuracy'])
return model
def sequential_nn_model(X_train, y_train):
model = Sequential([
Dense(100, activation='relu', input_shape=(X_train.shape[1], )),
Dense(40, activation='relu'),
Dense(20, activation='relu'),
Dense(1, activation='relu')
])
model.compile(optimizer='nadam',
loss=rmsle,
metrics=['mean_squared_logarithmic_error'])
hist = model.fit(X_train, y_train, epochs=50)
return model
def create_model():
checkpoint = ModelCheckpoint('sdr_model.h5',
monitor='accuracy',
verbose=1,
save_best_only=True,
mode='max')
callbacks_list = [checkpoint]
gray_data = np.load("npy_data/gray_dataset.npy")
color_data = np.load("npy_data/color_dataset.npy")
# img_pixel_dataset = np.load("npy_data/img_pixel_dataset.npy")
label = np.load("npy_data/label.npy")
# dataset = pre_processing.npy_dataset_concatenate(gray_data, color_data)
dataset = pre_processing.npy_dataset_concatenate(gray_data, color_data)
# corr_matrix = np.corrcoef(dataset)
# print(corr_matrix)
le = preprocessing.LabelEncoder()
label = le.fit_transform(label)
x_train, x_test, y_train, y_test = train_test_split(dataset,
label,
test_size=0.20,
shuffle=True)
model = Sequential()
model.add(Dense(14, input_dim=14, activation=None))
model.add(Dense(128, activation='tanh'))
model.add(Dense(256, activation='sigmoid'))
model.add(Dense(3, activation='softmax'))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train,
y_train,
epochs=150,
verbose=0,
batch_size=20,
shuffle=True,
callbacks=callbacks_list)
pred_y_test = model.predict_classes(x_test)
acc_model = accuracy_score(y_test, pred_y_test)
print("Prediction Acc model:", acc_model)
print("Org. Labels:", y_test[:30])
print("Pred Labels:", (pred_y_test[:30]))
# c_report = classification_report(y_test, pred_y_test, zero_division=0)
# print(c_report)
print("\n\n")
def get_pen_cnn(input_data, num_labels):
model = Sequential()
model.add(Conv2D(64, kernel_size=(3, 3), activation='relu', input_shape=input_data.shape))
model.add(MaxPooling2D(pool_size=2, strides=2))
model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(Flatten())
model.add(Dense(500, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_labels, activation='softmax'))
opt = Adam(learning_rate=.0003)
model.compile(loss='categorical_crossentropy', opt=opt, metrics=['accuracy'])
return model
def __init__(self,
state_size: int,
action_size: int,
representation_size: int,
max_value: int,
hidden_neurons: int = 64,
weight_decay: float = 1e-4,
representation_activation: str = 'tanh'):
self.state_size = state_size
self.action_size = action_size
self.value_support_size = math.ceil(math.sqrt(max_value)) + 1
regularizer = regularizers.l2(weight_decay)
representation_network = Sequential([
Dense(hidden_neurons,
activation='relu',
kernel_regularizer=regularizer),
Dense(representation_size,
activation=representation_activation,
kernel_regularizer=regularizer)
])
value_network = Sequential([
Dense(hidden_neurons,
activation='relu',
kernel_regularizer=regularizer),
Dense(self.value_support_size, kernel_regularizer=regularizer)
])
policy_network = Sequential([
Dense(hidden_neurons,
activation='relu',
kernel_regularizer=regularizer),
Dense(action_size, kernel_regularizer=regularizer)
])
dynamic_network = Sequential([
Dense(hidden_neurons,
activation='relu',
kernel_regularizer=regularizer),
Dense(representation_size,
activation=representation_activation,
kernel_regularizer=regularizer)
])
reward_network = Sequential([
Dense(16, activation='relu', kernel_regularizer=regularizer),
Dense(1, kernel_regularizer=regularizer)
])
super().__init__(representation_network, value_network, policy_network,
dynamic_network, reward_network)
def __init__(self,
num_hidden,
window,
end_time,
future_target_size,
validation_ratio,
validation_freq,
effective_factor,
mean_absolute_percentage_error=None,
describe=None,
epoc=10,
metric_sender=None):
self.__num_hidden = num_hidden
self.__future_target = future_target_size
self.__window = window
self.__epochs = epoc
self.__mean_absolute_percentage_error = mean_absolute_percentage_error
self.__end_time = end_time
self.__effective_factor = effective_factor
self.__model = Sequential([
LSTM(num_hidden,
input_shape=np.zeros((window, len(effective_factor))).shape),
Dense(self.__future_target)
])
self.__model.compile(optimizer='adam', loss='mean_squared_error')
self.__validation_ratio = validation_ratio
self.__validation_freq = validation_freq
self.__fit_model = ModelType.LSTM
self.__describe = describe
self.__metric_collector = MetricCollector(epochs=self.__epochs,
metric_sender=metric_sender)
def create_model(embeddings_file: str, input_size, input_length, hidden_size):
"""
Create simple regression model with a single embedding layer.
:param embeddings_file: embeddings file to load
:param input_size: size of input layer
:param hidden_size: size of embeddings
:return: Keras model
"""
model = Sequential()
model.add(
Embedding(input_size,
hidden_size,
input_length=input_length,
name='embedding'))
model.add(keras.layers.Lambda(lambda x: keras.backend.sum(x, axis=1)))
#model.add(Flatten())
model.add(Dense(92, activation="sigmoid"))
if embeddings_file is not None:
embeddings = np.loadtxt(embeddings_file)
model.get_layer("embedding").set_weights([embeddings])
#model.summary()
return model
def build_network():
network = models.Sequential()
network.add(Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
network.add(MaxPooling2D((2, 2)))
network.add(Conv2D(64, (3, 3), activation='relu'))
network.add(MaxPooling2D((2, 2)))
network.add(Conv2D(64, (3, 3), activation='relu'))
network.add(Flatten())
network.add(Dense(64, activation='relu'))
# network.add(Dense(32, activation='relu'))
network.add(Dense(10, activation='softmax'))
network.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return network
def get_cnn(input_data, num_labels):
model = Sequential()
model.add(Conv2D(16, kernel_size=2, activation='relu', input_shape=input_data.shape))
model.add(Conv2D(64, kernel_size=3, activation='relu'))
model.add(Conv2D(128, kernel_size=3, activation='relu'))
model.add(Flatten())
model.add(Dense(num_labels, activation='softmax'))
opt = Adamax(learning_rate=LEARNING_RATE)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
return model
def __init__(self):
super(FaceModel, self).__init__()
self.base_model = InceptionResNetV2(
input_shape=(IMG_SIZE, IMG_SIZE, 3),
include_top=False,
weights='imagenet',
pooling='avg'
) # pooling_avg applies GlobalAveragePooling2D at the end
# Map inceptionResnetV2 output to embeddings
self.embedding_layer = Dense(EMB_SIZE)
def create_model():
model = Sequential()
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
training_data_generator = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.1,
zoom_range=0.1,
horizontal_flip=True)
training_generator = training_data_generator.flow_from_directory(
data_dir,
target_size=(300, 300),
batch_size=5,
class_mode="categorical")
model.fit_generator(training_generator, epochs=3)
return model
def get_stacked_cnn_lstm(input_data, num_labels):
model = Sequential()
model.add(TimeDistributed(Conv2D(16, kernel_size=3, activation='relu', input_shape=input_data.shape)))
model.add(TimeDistributed(Conv2D(64, kernel_size=5, activation='relu')))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(units=2048))
model.add(Dense(num_labels, activation='softmax'))
opt = Adamax(learning_rate=LEARNING_RATE)
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
def prepare_model(self, number_of_unique_output_values):
self.model.add(
CuDNNLSTM(self.first_lstm_layer_size,
batch_input_shape=(None, self.sequence_length, 1),
return_sequences=True))
self.model.add(Dropout(self.dropout_rate))
self.model.add(CuDNNLSTM(self.second_lstm_layer_size))
self.model.add(Dropout(self.dropout_rate))
self.model.add(Dense(number_of_unique_output_values))
self.model.add(Activation('softmax'))
self.model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
def get_clstm(input_data, num_labels):
model = Sequential()
model.add(ConvLSTM2D(filters=16, kernel_size=(3, 3),
input_shape=input_data.shape,
padding='same', return_sequences=True))
model.add(BatchNormalization())
model.add(ConvLSTM2D(filters=64, kernel_size=(5, 5),
padding='same', return_sequences=False))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(num_labels, activation='softmax'))
opt = Adamax(learning_rate=LEARNING_RATE)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
return model
def create_model(step: Tensorflow2ModelStep):
"""
Create a TensorFlow v2 Multi-Layer-Perceptron Model.
:param step: The base Neuraxle step for TensorFlow v2 (Tensorflow2ModelStep)
:return: TensorFlow v2 Keras model
"""
# shape: (batch_size, input_dim)
inputs = Input(
shape=(step.hyperparams['input_dim']),
batch_size=None,
dtype=tf.dtypes.float32,
name='inputs',
)
dense_layers = [
Dense(units=step.hyperparams['hidden_dim'],
kernel_initializer=step.hyperparams['kernel_initializer'],
activation=step.hyperparams['activation'],
input_shape=(step.hyperparams['input_dim'], ))
]
hidden_dim = step.hyperparams['hidden_dim']
for i in range(step.hyperparams['n_dense_layers'] - 1):
hidden_dim *= step.hyperparams['hidden_dim_layer_multiplier']
dense_layers.append(
Dense(units=int(hidden_dim),
activation=step.hyperparams['activation'],
kernel_initializer=step.hyperparams['kernel_initializer']))
for layer in dense_layers:
outputs = layer(inputs)
softmax_layer = Dense(step.hyperparams['n_classes'], activation='softmax')
outputs = softmax_layer(outputs)
return Model(inputs=inputs, outputs=outputs)
def _make_layers(self):
# Create the model
model = Sequential()
model.add(
Conv2D(32,
kernel_size=(3, 3),
activation='relu',
input_shape=(48, 48, 1)))
model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(7, activation='softmax'))
return model
def create_model(embeddings_file: str, input_size, hidden_size, output_size):
"""
Create simple regression model with a single embedding layer.
:param embeddings_file: embeddings file to load
:param input_size: size of input layer
:param hidden_size: size of embeddings
:param output_size: size of output layer
:return: Keras model
"""
model = Sequential()
model.add(
Embedding(input_size, hidden_size, input_length=1, name='embedding'))
if embeddings_file is not None:
embeddings = np.loadtxt(embeddings_file)
model.get_layer("embedding").set_weights([embeddings])
model.add(Flatten())
model.add(Dense(output_size, activation="sigmoid"))
return model
contexts = contexts[0:train_size]
vocab_size = np.amax(pairs) + 1
input_target = Input((1, ))
input_context = Input((1, ))
embedding = Embedding(vocab_size, vector_dim, input_length=1, name='embedding')
target = embedding(input_target)
target = Reshape((vector_dim, 1))(target)
context = embedding(input_context)
context = Reshape((vector_dim, 1))(context)
# now perform the dot product operation to get a similarity measure
dot_product = dot([target, context], axes=1)
dot_product = Reshape((1, ))(dot_product)
# add the sigmoid output layer
output = Dense(1, activation='sigmoid')(dot_product)
model = Model(inputs=[input_target, input_context], outputs=output)
model.compile(loss='binary_crossentropy', optimizer='rmsprop')
model.summary()
history = model.fit(x=[targets, contexts],
y=labels,
batch_size=1,
epochs=1,
validation_split=0.0)
print("Saving the embeddings layer")
weights = model.get_layer("embedding").get_weights()[0]
np.savetxt(
model.add(MaxPool2D(2, 2))
model.add(Dropout(0.2))
model.add(
Conv2D(256,
3,
padding="same",
activation="relu",
kernel_initializer="he_uniform"))
model.add(Conv2D(256, 3, padding="same", activation="relu"))
model.add(BatchNormalization())
model.add(MaxPool2D(2, 2))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(200, activation="relu"))
model.add(Dropout(0.5))
#model.add(Dense(1,activation="sigmoid"))
model.add(Dense(len(classes), activation="softmax"))
model.compile(optimizer="adam",
loss="sparse_categorical_crossentropy",
metrics=["accuracy"])
history = model.fit_generator(train_generator,
steps_per_epoch=len(train_generator),
epochs=8,
verbose=1)
model.save(id_path + "./00.h5")
else:
model = keras.models.load_model(modelpath)
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
model = tf.keras.models.Sequential()
#-------------MOD------------------------
model.add(
Conv2D(16, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(10, activation='softmax'))
#-------------------------------------
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test, verbose=2)
print("Saving model to disk \n")
mp = "iris_model.h5"
model.save(mp)
# print(X_train.shape, X_val.shape, X_test.shape, y_train.shape, y_val.shape, y_test.shape)
# model = Sequential([
# Dense(100, activation='relu', input_shape=(57,)),
# Dense(40, activation='relu'),
# Dense(20, activation='relu'),
# Dense(1, activation='relu')
# ])
# model.compile(optimizer='adam',
# loss='mean_squared_logarithmic_error',
# metrics=['mean_squared_logarithmic_error'])
# hist = model.fit(X, y, epochs=100)
NNmodel = Sequential()
NNmodel.add(Dense(57, kernel_initializer='normal', activation='relu'))
NNmodel.add(Dense(100, kernel_initializer='normal', activation='relu'))
NNmodel.add(Dense(40, kernel_initializer='normal', activation='relu'))
NNmodel.add(Dense(20, kernel_initializer='normal', activation='relu'))
NNmodel.add(Dense(1, kernel_initializer='normal', activation='relu'))
NNmodel.compile(loss='mean_squared_logarithmic_error',
optimizer='adam',
metrics=['mean_squared_logarithmic_error'])
df_test['weather_4'] = 0
df_test = df_test[[
x for x in all_columns if x.startswith(tuple(train_columns))
]]
LSTM(hidden_layer_size, activation=tf.nn.relu,
return_sequences=True,
input_shape=(X_train.shape[1], X_train.shape[2])),
)
model.add(
Dropout(0.2)
)
model.add(
LSTM(hidden_layer_size, activation=tf.nn.relu,
return_sequences=True,
input_shape=(X_train.shape[1], X_train.shape[2])),
)
model.add(
Dropout(0.2)
)
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
model.load_weights('models/deep_weights.rnn')
predicted = model.predict(X_val)
predicted2 = [undo_normalize(y, petr4_frame['Close']) for y in np.ravel(predicted)]
y_val2 = [undo_normalize(y, petr4_frame['Close']) for y in np.ravel(y_val)]
plt.plot(range(0, past_history), [undo_normalize(x, petr4_frame['Close']) for x in X_val[0]], label='history')
plt.plot(range(len(X_val[0]), len(X_val[0]) + past_history), predicted2, '*', label='predict')
plt.plot(range(len(X_val[0]), len(X_val[0]) + past_history), y_val2, 'o', label='real', alpha=0.5)
plt.legend()
plt.show()
print(model.evaluate(X_val, y_val, verbose=2))
# Define an input sequence and process it.
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = LSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
# Run training
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit([encoder_input_data, decoder_input_data],
decoder_target_data,
batch_size=batch_size,
epochs=epochs,
validation_split=0.2)