def setup_sentence_model():
X_train = get_sentence_embeddings(headlines_train)
X_eval = get_sentence_embeddings(headlines_eval)
model = Sequential()
model.add(
Dense(256,
input_dim=512,
activation='relu',
bias_initializer='zeros',
kernel_regularizer=regularizers.l2(args.lambd)))
model.add(Dropout(0.25))
model.add(Dense(1, activation='sigmoid', bias_initializer='zeros'))
model.compile(
optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy',
km.binary_precision(),
km.binary_recall()])
# Fit the model
model.fit(X_train,
labels_train,
epochs=200,
batch_size=args.batch_size,
callbacks=callbacks,
validation_data=(X_eval, labels_eval))
return model
def get_conv_model(input_shape):
model = Sequential()
model.add(
Conv2D(128, (3, 3),
activation='relu',
strides=(1, 1),
padding='same',
input_shape=input_shape))
model.add(
Conv2D(64, (3, 3), activation='relu', strides=(1, 1), padding='same'))
model.add(
Conv2D(32, (3, 3), activation='relu', strides=(1, 1), padding='same'))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.summary()
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['acc',
km.binary_precision(),
km.binary_recall()])
return model
def gruModel(embeddingMatrix, maxDataLenght, embeddingVectorLength,
numAttributes, numNeurons):
model = Sequential()
model.add(
Embedding(input_dim=numAttributes,
output_dim=embeddingVectorLength,
weights=[embeddingMatrix],
input_length=maxDataLenght,
trainable=False))
model.add(GRU(numNeurons, return_sequences=False))
model.add(Dropout(0.2))
model.add(
Dense(1,
activation='sigmoid',
kernel_regularizer=regularizers.l2(0.001)))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=[
'accuracy',
km.binary_f1_score(),
km.binary_precision(),
km.binary_recall()
])
return model
def get_binary_model(input_shape=128):
model = Sequential()
model.add(
Dense(128,
activation='relu',
kernel_initializer='random_normal',
input_dim=input_shape))
model.add(Dense(256, activation='relu',
kernel_initializer='random_normal'))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu',
kernel_initializer='random_normal'))
model.add(Dense(64, activation='relu', kernel_initializer='random_normal'))
model.add(Dense(32, activation='relu', kernel_initializer='random_normal'))
model.add(Dropout(0.5))
model.add(Dense(8, activation='relu', kernel_initializer='random_normal'))
model.add(
Dense(1, activation='sigmoid', kernel_initializer='random_normal'))
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['acc',
km.binary_precision(),
km.binary_recall()])
return model
def load_predict(pre_list):
# 清除session，避免重复调用出错
keras.backend.clear_session()
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
model_path = os.path.join(BASE_DIR, 'recommend', 'model.h5')
model = load_model(model_path,
custom_objects={
'binary_precision': km.binary_precision(),
'binary_recall': km.binary_recall(),
'binary_f1_score': km.f1_score()
})
predictions = model.predict(pre_list)
print(predictions)
return predictions
def load_object(root_folder, obj_descr_type, model_name, dataset,
refactoring_name):
if model_name == 'deep-learning' and obj_descr_type == 'model':
file_name = root_folder + "/" + obj_descr_type + "-" + model_name + "-" + dataset + "-" + refactoring_name.replace(
" ", "") + ".h5"
return keras_load_model(file_name,
custom_objects={
"binary_precision": binary_precision(),
"binary_recall": binary_recall()
})
else:
file_name = root_folder + "/" + obj_descr_type + "-" + model_name + "-" + dataset + "-" + refactoring_name.replace(
" ", "") + ".joblib"
return load(file_name)
def predic_unseen(model_name,
file_info,
unseen_files,
data_path,
threshold=0.5):
# Load Model
dependencies = {
'binary_precision': km.binary_precision(),
'binary_recall': km.binary_recall()
}
model = load_model(data_path + 'Models/' + model_name,
custom_objects=dependencies)
# Load data
test_x = []
test_y = []
for j in range(len(unseen_files)):
# Get the file name and read the data
file = file_info[file_info.fname == unseen_files[j]].fname.iloc[0]
audio_data = pickle.load(open(data_path + 'VGG/' + file, 'rb'))
test_x.append(audio_data)
# Get the class label
label = file_info[file_info.fname == unseen_files[j]].label.iloc[0]
test_y.append(np.repeat([label], (len(audio_data))))
# Make predictions
test_x = [response for sublist in test_x for response in sublist]
test_y = [response for sublist in test_y for response in sublist]
test_x = np.array(test_x)
test_y = np.array(test_y)
y_pred = model.predict(test_x)
y_pred_th = (y_pred > threshold)
# Confusion matrix
cm_test = confusion_matrix(test_y, y_pred_th)
print(cm_test)
# Recall
tpr_test = recall_score(test_y, y_pred_th)
print('TPR: ', tpr_test)
# Precision
precision_test = precision_score(test_y, y_pred_th)
print('Precision: ', precision_test)
# F1 score
fscore_test = f1_score(test_y, y_pred_th)
print('F1 score: ', fscore_test)
def load_models(folder, streams):
models_list = []
for stream in streams:
print('\nLoading', stream, 'model\n')
models_list.append(
load_model(folder + stream + '_best-weights.h5',
custom_objects={
'binary_precision':
keras_metrics.binary_precision(),
'binary_recall': keras_metrics.binary_recall()
}))
return models_list
def compile_model(self):
metrics = [km.binary_precision(0), km.binary_recall(0)]
self.NeuMF.compile(optimizer=SGD(lr=LEARN_RATE),
loss='binary_crossentropy',
metrics=metrics)
# update history dict
self.history['precision'] = []
self.history['recall'] = []
self.history['val_precision'] = []
self.history['val_recall'] = []
self.history['loss'] = []
self.history['val_loss'] = []
print('compiling NeuMF Model ...')
def get_custom_activations_dict(filepath=None):
"""
Import all implemented custom activation functions so they can be used when
loading a Keras model.
Parameters
----------
filepath : Optional[str]
Path to json file containing additional custom objects.
"""
from snntoolbox.utils.utils import binary_sigmoid, binary_tanh, \
ClampedReLU, LimitedReLU, NoisySoftplus
import keras_metrics as km
# Todo: We should be able to load a different activation for each layer.
# Need to remove this hack:
activation_str = 'relu_Q1.4'
activation = get_quantized_activation_function_from_string(activation_str)
custom_objects = {
'binary_sigmoid': binary_sigmoid,
'binary_tanh': binary_tanh,
# Todo: This should work regardless of the specific attributes of the
# ClampedReLU class used during training.
'clamped_relu': ClampedReLU(),
'LimitedReLU': LimitedReLU,
'relu6': LimitedReLU({'max_value': 6}),
activation_str: activation,
'Noisy_Softplus': NoisySoftplus,
'precision': precision,
'binary_precision': km.binary_precision(label=0),
'binary_recall': km.binary_recall(label=0),
'activity_regularizer': keras.regularizers.l1}
if filepath is not None and filepath != '':
with open(filepath) as f:
kwargs = json.load(f)
for key in kwargs:
if 'LimitedReLU' in key:
custom_objects[key] = LimitedReLU(kwargs[key])
return custom_objects
def get_recurrent_model(input_shape):
model = Sequential()
model.add(LSTM(128, return_sequences=True, input_shape=input_shape))
model.add(LSTM(128, return_sequences=True))
model.add(Dropout(0.5))
model.add(TimeDistributed(Dense(64, activation='relu')))
model.add(TimeDistributed(Dense(32, activation='relu')))
model.add(TimeDistributed(Dense(16, activation='relu')))
model.add(TimeDistributed(Dense(8, activation='relu')))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['acc',
km.binary_precision(),
km.binary_recall()])
return model
def build_tf_graph(self):
'''keras to tf conversion'''
# loading keras model
K.set_learning_phase(0)
model = load_model(self.keras_model_path,
custom_objects={
'binary_precision': km.binary_precision(),
'binary_recall': km.binary_recall()
})
# create frozen graph of the keras model
frozen_graph = self.__freeze_session__(
K.get_session(),
output_names=[out.op.name for out in model.outputs])
# save model as .pb file
tf.train.write_graph(frozen_graph,
'saved_models/tf_model',
self.tf_path,
as_text=False)
def main(input_path, model_path):
model = load_model(model_path,
custom_objects={
"binary_precision":
keras_metrics.binary_precision(),
"binary_recall": keras_metrics.binary_recall()
})
allowed_filetypes = [
'.avi', '.wmv', '.mpg', '.mov', '.mp4', '.mkv', '.3gp', '.webm', '.ogv'
]
videos_path = []
if os.path.isfile(input_path) and input_path.lower().endswith(
tuple(allowed_filetypes)):
videos_path = [input_path]
elif os.path.isdir(input_path):
search_path = os.path.join(input_path, '**')
for ext in allowed_filetypes:
videos_path.extend(glob2.glob(os.path.join(search_path,
'*' + ext)))
else:
print("Not a valid input.")
videos_path = natsorted(videos_path)
for video_path in videos_path:
folder = os.path.dirname(os.path.abspath(video_path))
filename = os.path.basename(video_path)
json_path = os.path.join(folder, filename.split('.')[0] + '.json')
print(video_path)
if os.path.isfile(json_path):
continue
else:
game_inference(model,
video_path,
json_path,
samples=24,
height=224,
width=224)
def Lstm(dataInput, maxDataLength):
train, test = train_test_split(dataInput, test_size=0.2)
xTrain, yTrain = list(zip(*train))
xTest, yTest = list(zip(*test))
yTrain = np.array(yTrain)
yTest = np.array(yTest)
xTrain = sequence.pad_sequences(xTrain, maxlen=maxDataLength)
xTest = sequence.pad_sequences(xTest, maxlen=maxDataLength)
embedding_vector_length = 32
model = Sequential()
model.add(
Embedding(NUM_OF_ATTRIBUTES,
embedding_vector_length,
input_length=maxDataLength))
model.add(Bidirectional(LSTM(NUM_OF_NEURONS, return_sequences=False)))
model.add(Dropout(0.2))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=[
'accuracy',
km.binary_f1_score(),
km.binary_precision(),
km.binary_recall()
])
model.fit(xTrain,
yTrain,
validation_data=(xTest, yTest),
epochs=NUM_OF_EPOCHS,
batch_size=512,
verbose=0)
scores = model.evaluate(xTest, yTest, verbose=0)
for i in range(1, 5):
print("%s : %.2f%%" % (model.metrics_names[i], scores[i] * 100))
print("========================================================")
def Build_Model_CNN_Text(word_index,
embedding_index,
number_of_classes,
MAX_SEQUENCE_LENGTH,
EMBEDDING_DIM,
sparse_categorical,
min_hidden_layer_cnn,
max_hidden_layer_cnn,
min_nodes_cnn,
max_nodes_cnn,
random_optimizor,
dropout,
simple_model=False,
_l2=0.01,
lr=1e-3):
"""
def buildModel_CNN(word_index,embedding_index,number_of_classes,MAX_SEQUENCE_LENGTH,EMBEDDING_DIM,Complexity=0):
word_index in word index ,
embedding_index is embeddings index, look at data_helper.py
number_of_classes is number of classes,
MAX_SEQUENCE_LENGTH is maximum lenght of text sequences,
EMBEDDING_DIM is an int value for dimention of word embedding look at data_helper.py
Complexity we have two different CNN model as follows
F=0 is simple CNN with [1 5] hidden layer
Complexity=2 is more complex model of CNN with filter_length of range [1 10]
"""
model = Sequential()
if simple_model:
embedding_matrix = np.zeros((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
embedding_vector = embedding_index.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all-zeros.
embedding_matrix[i] = embedding_vector
else:
embedding_matrix[i] = embedding_index['UNK']
model.add(
Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True))
values = list(range(min_nodes_cnn, max_nodes_cnn))
Layer = list(range(min_hidden_layer_cnn, max_hidden_layer_cnn))
Layer = random.choice(Layer)
for i in range(0, Layer):
Filter = random.choice(values)
model.add(
Conv1D(Filter,
5,
activation='relu',
kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
model.add(MaxPooling1D(5))
model.add(Flatten())
Filter = random.choice(values)
model.add(Dense(Filter, activation='relu', kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
Filter = random.choice(values)
model.add(Dense(Filter, activation='relu', kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
if number_of_classes == 2:
model.add(
Dense(1, activation='sigmoid', kernel_regularizer=l2(_l2)))
model_tmp = model
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
model.add(
Dense(number_of_classes,
activation='softmax',
kernel_regularizer=l2(_l2)))
model_tmp = model
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
else:
embedding_matrix = np.zeros((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
embedding_vector = embedding_index.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all-zeros.
embedding_matrix[i] = embedding_vector
else:
embedding_matrix[i] = embedding_index['UNK']
embedding_layer = Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True)
# applying a more complex convolutional approach
convs = []
values_layer = list(range(min_hidden_layer_cnn, max_hidden_layer_cnn))
filter_sizes = []
layer = random.choice(values_layer)
print("Filter ", layer)
for fl in range(0, layer):
filter_sizes.append((fl + 2))
values_node = list(range(min_nodes_cnn, max_nodes_cnn))
node = random.choice(values_node)
print("Node ", node)
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH, ), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
for fsz in filter_sizes:
l_conv = Conv1D(node, kernel_size=fsz,
activation='relu')(embedded_sequences)
l_pool = MaxPooling1D(5)(l_conv)
#l_pool = Dropout(0.25)(l_pool)
convs.append(l_pool)
l_merge = Concatenate(axis=1)(convs)
l_cov1 = Conv1D(node, 5, activation='relu')(l_merge)
l_cov1 = Dropout(dropout)(l_cov1)
l_pool1 = MaxPooling1D(5)(l_cov1)
l_cov2 = Conv1D(node, 5, activation='relu')(l_pool1)
l_cov2 = Dropout(dropout)(l_cov2)
l_pool2 = MaxPooling1D(30)(l_cov2)
l_flat = Flatten()(l_pool2)
l_dense = Dense(1024, activation='relu')(l_flat)
l_dense = Dropout(dropout)(l_dense)
l_dense = Dense(512, activation='relu')(l_dense)
l_dense = Dropout(dropout)(l_dense)
if number_of_classes == 2:
preds = Dense(1, activation='sigmoid')(l_dense)
else:
preds = Dense(number_of_classes, activation='softmax')(l_dense)
model = Model(sequence_input, preds)
model_tmp = model
if number_of_classes == 2:
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
def Build_Model_RNN_Text(word_index,
embedding_index,
number_of_classes,
MAX_SEQUENCE_LENGTH,
EMBEDDING_DIM,
sparse_categorical,
min_hidden_layer_rnn,
max_hidden_layer_rnn,
min_nodes_rnn,
max_nodes_rnn,
random_optimizor,
dropout,
use_cuda=True,
use_bidirectional=True,
_l2=0.01,
lr=1e-3):
"""
def buildModel_RNN(word_index, embedding_index, number_of_classes, MAX_SEQUENCE_LENGTH, EMBEDDING_DIM, sparse_categorical):
word_index in word index ,
embedding_index is embeddings index, look at data_helper.py
number_of_classes is number of classes,
MAX_SEQUENCE_LENGTH is maximum lenght of text sequences
"""
Recurrent = CuDNNGRU if use_cuda else GRU
model = Sequential()
values = list(range(min_nodes_rnn, max_nodes_rnn + 1))
values_layer = list(range(min_hidden_layer_rnn - 1, max_hidden_layer_rnn))
layer = random.choice(values_layer)
print(layer)
embedding_matrix = np.zeros((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items():
embedding_vector = embedding_index.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all-zeros.
embedding_matrix[i] = embedding_vector
else:
embedding_matrix[i] = embedding_index['UNK']
model.add(
Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True))
gru_node = random.choice(values)
print(gru_node)
for i in range(0, layer):
if use_bidirectional:
model.add(
Bidirectional(
Recurrent(gru_node,
return_sequences=True,
kernel_regularizer=l2(_l2))))
else:
model.add(
Recurrent(gru_node,
return_sequences=True,
kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
if use_bidirectional:
model.add(
Bidirectional(Recurrent(gru_node, kernel_regularizer=l2(_l2))))
else:
model.add(Recurrent(gru_node, kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
model.add(Dense(256, activation='relu', kernel_regularizer=l2(_l2)))
if number_of_classes == 2:
model.add(Dense(1, activation='sigmoid', kernel_regularizer=l2(_l2)))
model_tmp = model
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
model.add(
Dense(number_of_classes,
activation='softmax',
kernel_regularizer=l2(_l2)))
model_tmp = model
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
def Build_Model_RNN_Image(shape, number_of_classes, sparse_categorical,
min_nodes_rnn, max_nodes_rnn, random_optimizor,
dropout):
"""
def Image_model_RNN(num_classes,shape):
num_classes is number of classes,
shape is (w,h,p)
"""
values = list(range(min_nodes_rnn - 1, max_nodes_rnn))
node = random.choice(values)
x = Input(shape=shape)
# Encodes a row of pixels using TimeDistributed Wrapper.
encoded_rows = TimeDistributed(CuDNNLSTM(node,
recurrent_dropout=dropout))(x)
node = random.choice(values)
# Encodes columns of encoded rows.
encoded_columns = CuDNNLSTM(node, recurrent_dropout=dropout)(encoded_rows)
# Final predictions and model.
#prediction = Dense(256, activation='relu')(encoded_columns)
if number_of_classes == 2:
prediction = Dense(1, activation='sigmoid')(encoded_columns)
else:
prediction = Dense(number_of_classes,
activation='softmax')(encoded_columns)
model = Model(x, prediction)
model_tmp = model
if number_of_classes == 2:
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
def Build_Model_CNN_Image(shape, number_of_classes, sparse_categorical,
min_hidden_layer_cnn, max_hidden_layer_cnn,
min_nodes_cnn, max_nodes_cnn, random_optimizor,
dropout):
"""""
def Image_model_CNN(num_classes,shape):
num_classes is number of classes,
shape is (w,h,p)
""" ""
model = Sequential()
values = list(range(min_nodes_cnn, max_nodes_cnn))
Layers = list(range(min_hidden_layer_cnn, max_hidden_layer_cnn))
Layer = random.choice(Layers)
Filter = random.choice(values)
model.add(Conv2D(Filter, (3, 3), padding='same', input_shape=shape))
model.add(Activation('relu'))
model.add(Conv2D(Filter, (3, 3)))
model.add(Activation('relu'))
for i in range(0, Layer):
Filter = random.choice(values)
model.add(Conv2D(Filter, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(dropout))
if number_of_classes == 2:
model.add(Dense(1, activation='sigmoid', kernel_constraint=maxnorm(3)))
model_tmp = model
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
model.add(
Dense(number_of_classes,
activation='softmax',
kernel_constraint=maxnorm(3)))
model_tmp = model
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
def Build_Model_DNN_Text(shape,
number_of_classes,
sparse_categorical,
min_hidden_layer_dnn,
max_hidden_layer_dnn,
min_nodes_dnn,
max_nodes_dnn,
random_optimizor,
dropout,
_l2=0.01,
lr=1e-3):
"""
buildModel_DNN_Tex(shape, number_of_classes,sparse_categorical)
Build Deep neural networks Model for text classification
Shape is input feature space
number_of_classes is number of classes
"""
model = Sequential()
layer = list(range(min_hidden_layer_dnn, max_hidden_layer_dnn))
node = list(range(min_nodes_dnn, max_nodes_dnn))
Numberof_NOde = random.choice(node)
nLayers = random.choice(layer)
Numberof_NOde_old = Numberof_NOde
model.add(
Dense(Numberof_NOde,
input_dim=shape,
activation='relu',
kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
for i in range(0, nLayers):
Numberof_NOde = random.choice(node)
model.add(
Dense(Numberof_NOde,
input_dim=Numberof_NOde_old,
activation='relu',
kernel_regularizer=l2(_l2)))
model.add(Dropout(dropout))
Numberof_NOde_old = Numberof_NOde
if number_of_classes == 2:
model.add(Dense(1, activation='sigmoid', kernel_regularizer=l2(_l2)))
model_tmp = model
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
model.add(
Dense(number_of_classes,
activation='softmax',
kernel_regularizer=l2(_l2)))
model_tmp = model
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor, lr),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
# Add Embedding layer
# The final sigmoid layer outputs probability values between [0, 1]
model = models.Sequential()
model.add(layers.Embedding(10000, 8, input_length=data.shape[1]))
model.add(layers.Flatten())
model.add(layers.Dense(1, activation='sigmoid'))
# =========================
# Train model
# =========================
# As the model outputs probabilities, binary crossentropy is the best loss
# metric as it measures the distance between probability distributions
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=[km.binary_precision(),
km.binary_recall()])
history = model.fit(x_train,
y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))
# Prep history dictionary
precision = history.history['precision']
val_precision = history.history['val_precision']
recall = history.history['recall']
val_recall = history.history['val_recall']
epochs = range(1, len(precision) + 1)
BATCH = 64
EPOCHS = 100
# Definir el modelo:
model = GlandsDetector(input_shape=(32,32,6), output=2)
# Definir el optimizador:
adam = Adam()
# Compilar el modelo:
model.compile(
loss='binary_crossentropy',
optimizer=adam,
metrics=['binary_accuracy', km.binary_f1_score(label=1),
km.binary_precision(label=1), km.binary_recall(label=1)]
)
callback_list = [LearningRateScheduler(step_decay)]
# Entrenar:
history = model.fit(
X_train,
y_train_ohe,
batch_size=BATCH,
epochs=EPOCHS,
validation_data=(X_val, y_val_ohe),
class_weight=class_weights,
callbacks=callback_list,
verbose=2
)
output_shape)
callback = ModelSaveBestAvgAcc(filepath="model-{epoch:02d}-{avgacc:.2f}.hdf5",
verbose=True,
cond=filter_val_f1score)
losses = []
for i in range(0, 6):
losses.append(binary_focal_loss(gamma=2.))
model = get_model(input_shape)
model.compile(optimizer=opt.Adam(lr=1e-4),
loss=losses,
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score()
])
model.summary()
model.fit_generator(gen_train,
steps_per_epoch=len(dataset_train.image_ids) // batch_size,
epochs=epochs,
validation_data=gen_val,
validation_steps=len(dataset_val.image_ids) // batch_size,
callbacks=[callback],
verbose=2)
print('fine')
def __init__(self, nn_rank_embedding_model, opts):
self.opts = opts
self.dense_dims = opts.dense_dims
self.query_title_model = nn_rank_embedding_model['query-title']
self.query_abstract_model = nn_rank_embedding_model['query-abstract']
self.candidate_title_model = nn_rank_embedding_model['candidate-title']
self.candidate_abstract_model = nn_rank_embedding_model[
'candidate-abstract']
model_inputs = [
self.query_title_model.input, self.candidate_title_model.input,
self.query_abstract_model.input,
self.candidate_abstract_model.input
]
pre_dense_network_output = []
cos_sim_text = cosine_distance(self.query_title_model.output,
self.candidate_title_model.output,
self.dense_dims, True)
cos_sim_abstract = cosine_distance(
self.query_abstract_model.output,
self.candidate_abstract_model.output, self.dense_dims, True)
pre_dense_network_output.append(cos_sim_text)
pre_dense_network_output.append(cos_sim_abstract)
for field in ['title', 'abstract']:
common_type_input = Input(
name='query-candidate-common-{}'.format(field), shape=(None, ))
elementwise_sparse = EmbeddingLayer(
input_dim=self.opts.n_features,
output_dim=1,
mask_zero=True,
name="{}-sparse-embedding".format(field),
activity_regularizer=l1(
self.opts.l1_lambda))(common_type_input)
pre_dense_network_output.append(
summation_layer()(elementwise_sparse))
model_inputs.append(common_type_input)
citation_count_input = Input(shape=(1, ),
dtype='float32',
name='candidate-citation-count')
model_inputs.append(citation_count_input)
pre_dense_network_output.append(citation_count_input)
similarity_score_input = Input(shape=(1, ),
dtype='float32',
name='similarity-score')
model_inputs.append(similarity_score_input)
pre_dense_network_output.append(similarity_score_input)
input_to_dense_layer = Concatenate()(pre_dense_network_output)
output_dense_one = Dense(20, name='dense-1',
activation='elu')(input_to_dense_layer)
output_dense_two = Dense(20, name='dense-2',
activation='elu')(output_dense_one)
nn_rank_output = Dense(1,
kernel_initializer='one',
name='final-output',
activation='sigmoid')(output_dense_two)
self.model = Model(inputs=model_inputs, outputs=nn_rank_output)
self.model.compile(optimizer='nadam',
loss=triplet_loss,
metrics=[
'accuracy', mean_reciprocal_rank,
binary_precision(),
binary_recall(), f1_measure
])
self.callbacks = [
SaveModelWeights([('nn_rank', self.model)],
self.opts.weights_directory,
self.opts.checkpoint_frequency)
]
def f1_m(y_true, y_pred):
precision = km.binary_precision(y_true, y_pred)
recall = km.binary_recall(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
beta_2=0.999,
epsilon=None,
decay=0.0,
amsgrad=False)
import keras_metrics as km
def f1_m(y_true, y_pred):
precision = km.binary_precision(y_true, y_pred)
recall = km.binary_recall(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
model.compile(optimizer=adam,
loss='binary_crossentropy',
metrics=['acc', km.binary_precision(),
km.binary_recall()])
print('model fitting...')
import numpy as np
import time
#def load_image(x, y):
# print(x[13])
# x[13] = np.load('./imagess'+x[13][1:]+'.npy').reshape(1,64,2048)
# x[6] = np.load('./imagess'+x[6][1:]+'.npy').reshape(1,64,2048)
# return x,y
#print('loading X_train images.. ')
#t_train = time.time()
#X_train = tf.data.Dataset.from_tensor_slices((X_train, y_train)).map(load_image)
#print(time.time()-t_train, 'loading X_test images..')
#t_test = time.time()
def __init__(self, model_file=None, weights_file=None):
self.model_file = model_file
self.weights_file = weights_file
self.l = 500
self.k = 13
self.m = 9
self.model = None
# See if there is a given model and weights file
if self.model_file is not None:
json_file = open(self.model_file, 'r')
loaded_model_json = json_file.read()
json_file.close()
self.model = model_from_json(loaded_model_json)
if self.weights in not None:
self.model.load_weights(weights_file)
else:
self.model = Sequential()
self.model.add(Embedding(xmax, k, input_length = l))
self.model.add(Lambda(lambda x: expand_dims(x, 3)))
self.model.add(Conv2D(512, (m, k), activation = "relu"))
self.model.add(MaxPooling2D(pool_size = (l - m + 1, 1)))
self.model.add(Flatten())
self.model.add(Dropout(0.5))
self.model.add(Dense(64, activation = "relu"))
self.model.add(Dense(16, activation = "relu"))
self.model.add(Dense(2, activation = "softmax"))
# Print out the model and compile it
self.model.summary()
self.model.compile(optimizer = "adam", loss = "categorical_crossentropy", metrics = [keras_metrics.binary_precision(), keras_metrics.binary_recall()])
def Build_Model_DNN_Image(shape, number_of_classes, sparse_categorical,
min_hidden_layer_dnn, max_hidden_layer_dnn,
min_nodes_dnn, max_nodes_dnn, random_optimizor,
dropout):
'''
buildModel_DNN_image(shape, number_of_classes,sparse_categorical)
Build Deep neural networks Model for text classification
Shape is input feature space
number_of_classes is number of classes
'''
model = Sequential()
values = list(range(min_nodes_dnn, max_nodes_dnn))
Numberof_NOde = random.choice(values)
Lvalues = list(range(min_hidden_layer_dnn, max_hidden_layer_dnn))
nLayers = random.choice(Lvalues)
print(shape)
model.add(Flatten(input_shape=shape))
model.add(Dense(Numberof_NOde, activation='relu'))
model.add(Dropout(dropout))
for i in range(0, nLayers - 1):
Numberof_NOde = random.choice(values)
model.add(Dense(Numberof_NOde, activation='relu'))
model.add(Dropout(dropout))
if number_of_classes == 2:
model.add(Dense(1, activation='sigmoid'))
model_tmp = model
model.compile(loss='binary_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.binary_precision(),
km.binary_recall(),
km.binary_f1_score(),
km.binary_true_positive(),
km.binary_true_negative(),
km.binary_false_positive(),
km.binary_false_negative()
])
else:
model.add(Dense(number_of_classes, activation='softmax'))
model_tmp = model
if sparse_categorical:
model.compile(loss='sparse_categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.sparse_categorical_precision(),
km.sparse_categorical_recall(),
km.sparse_categorical_f1_score(),
km.sparse_categorical_true_positive(),
km.sparse_categorical_true_negative(),
km.sparse_categorical_false_positive(),
km.sparse_categorical_false_negative()
])
else:
model.compile(loss='categorical_crossentropy',
optimizer=optimizors(random_optimizor),
metrics=[
'accuracy',
km.categorical_precision(),
km.categorical_recall(),
km.categorical_f1_score(),
km.categorical_true_positive(),
km.categorical_true_negative(),
km.categorical_false_positive(),
km.categorical_false_negative()
])
return model, model_tmp
finetune_model = Model(inputs=base_model.input, outputs=predictions)
return finetune_model
FC_LAYERS = [200, 50]
dropout = 0.5
finetune_model = build_finetune_model(base_model,
dropout=dropout,
fc_layers=FC_LAYERS,
num_classes=len(class_list))
recall = km.binary_recall(label=1)
precision = km.binary_precision(label=1)
finetune_model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=[
'accuracy', auc_roc,
km.binary_precision(label=1),
km.binary_recall(label=1)
])
print('fitting model')
class_weights = {0: 1., 1: 1.}
STEP_SIZE_TRAIN = train_gen.n // train_gen.batch_size
STEP_SIZE_VALID = val_gen.n // val_gen.batch_size
es = EarlyStopping(monitor='val_loss',
pr = np.zeros((3,4))
rec = np.zeros((3,4))
tp = np.zeros((3,4))
fp = np.zeros((3,4))
tn = np.zeros((3,4))
fn = np.zeros((3,4))
for i in range(3):
for j in range(4):
epochs, batch_size, n_neurons, dropout = epochs_arr[i], batch_size_arr[j], 1000, 0
n_timesteps, n_features, n_outputs = trainX.shape[1], trainX.shape[2], trainy.shape[1]
model = Sequential()
model.add(LSTM(n_neurons, input_shape=(n_timesteps,n_features)))
model.add(Dropout(dropout))
model.add(Dense(n_neurons, activation='relu'))
model.add(Dense(n_outputs, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['binary_accuracy', km.binary_precision(), km.binary_recall(), km.binary_true_positive(), km.binary_false_positive(), km.binary_true_negative(), km.binary_false_negative()])
# fit network
model.fit(trainX, trainy, epochs=epochs, batch_size=batch_size, verbose=1)
# evaluate model
_, ba[i,j], pr[i,j], rec[i,j], tp[i,j], fp[i,j], tn[i,j], fn[i,j] = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
#print(ba, pr, rec, tp, fp, tn, fn)
#print(hist.history)
np.savetxt('/home/mdzadik/CAN_data/pickles/ba_'+str(n_neurons)+'_'+str(dropout)+'.csv',ba,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/pr_'+str(n_neurons)+'_'+str(dropout)+'.csv',pr,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/rec_'+str(n_neurons)+'_'+str(dropout)+'.csv',rec,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/tp_'+str(n_neurons)+'_'+str(dropout)+'.csv',tp,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/fp_'+str(n_neurons)+'_'+str(dropout)+'.csv',fp,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/tn_'+str(n_neurons)+'_'+str(dropout)+'.csv',tn,delimiter=",")
np.savetxt('/home/mdzadik/CAN_data/pickles/fn_'+str(n_neurons)+'_'+str(dropout)+'.csv',fn,delimiter=",")
def get_predictions(text):
sequence = tokenizer.texts_to_sequences([text])
sequence = pad_sequences(sequence, maxlen=SEQUENCE_LENGTH)
model = load_model('Spam-model-compiled.h5',custom_objects={'binary_precision':keras_metrics.binary_precision(),'binary_recall':keras_metrics.binary_recall()})
prediction = model.predict(sequence)[0]
return int2label[np.argmax(prediction)]