replace softmax by sigmoid in final layer, also adjust dataset for that

This commit is contained in:
René Knaebel 2017-07-30 12:50:26 +02:00
parent b0da2de0ea
commit d97785f646
4 changed files with 16 additions and 23 deletions

View File

@ -6,7 +6,6 @@ from multiprocessing import Pool
import h5py import h5py
import numpy as np import numpy as np
import pandas as pd import pandas as pd
from keras.utils import np_utils
from tqdm import tqdm from tqdm import tqdm
logger = logging.getLogger('logger') logger = logging.getLogger('logger')
@ -119,7 +118,7 @@ def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10):
client_tr[:pos_idx.shape[-1]] = 1.0 client_tr[:pos_idx.shape[-1]] = 1.0
server_tr = server_tr[idx] server_tr = server_tr[idx]
client_tr = np_utils.to_categorical(client_tr, 2) # client_tr = np_utils.to_categorical(client_tr, 2)
return domain_tr, flow_tr, client_tr, server_tr return domain_tr, flow_tr, client_tr, server_tr

15
main.py
View File

@ -7,7 +7,6 @@ import pandas as pd
import tensorflow as tf import tensorflow as tf
from keras.callbacks import ModelCheckpoint, CSVLogger, EarlyStopping from keras.callbacks import ModelCheckpoint, CSVLogger, EarlyStopping
from keras.models import load_model from keras.models import load_model
from keras.utils import np_utils
from sklearn.utils import class_weight from sklearn.utils import class_weight
import arguments import arguments
@ -98,8 +97,8 @@ def main_hyperband():
def get_custom_class_weights(client_tr, server_tr): def get_custom_class_weights(client_tr, server_tr):
client = client_tr.value.argmax(1) if type(client_tr) != np.ndarray else client_tr.argmax(1) client = client_tr.value if type(client_tr) != np.ndarray else client_tr
server = server_tr.value.argmax(1) if type(server_tr) != np.ndarray else server_tr.argmax(1) server = server_tr.value if type(server_tr) != np.ndarray else server_tr
client_class_weight = class_weight.compute_class_weight('balanced', np.unique(client), client) client_class_weight = class_weight.compute_class_weight('balanced', np.unique(client), client)
server_class_weight = class_weight.compute_class_weight('balanced', np.unique(server), server) server_class_weight = class_weight.compute_class_weight('balanced', np.unique(server), server)
return { return {
@ -157,10 +156,10 @@ def main_train(param=None):
logger.info("compile model") logger.info("compile model")
custom_metrics = models.get_metric_functions() custom_metrics = models.get_metric_functions()
model.compile(optimizer='adam', model.compile(optimizer='adam',
loss='categorical_crossentropy', loss='binary_crossentropy',
metrics=['accuracy'] + custom_metrics) metrics=['accuracy'] + custom_metrics)
server_tr = np_utils.to_categorical(np.max(server_windows_tr, axis=1), 2) server_tr = np.max(server_windows_tr, axis=1)
if args.class_weights: if args.class_weights:
logger.info("class weights: compute custom weights") logger.info("class weights: compute custom weights")
@ -261,10 +260,10 @@ def main_new_model():
logger.info("compile model") logger.info("compile model")
custom_metrics = models.get_metric_functions() custom_metrics = models.get_metric_functions()
model.compile(optimizer='adam', model.compile(optimizer='adam',
loss='categorical_crossentropy', loss='binary_crossentropy',
metrics=['accuracy'] + custom_metrics) metrics=['accuracy'] + custom_metrics)
server_tr = np_utils.to_categorical(np.max(server_windows_tr, axis=1), 2) server_tr = np.max(server_windows_tr, axis=1)
if args.class_weights: if args.class_weights:
logger.info("class weights: compute custom weights") logger.info("class weights: compute custom weights")
@ -274,7 +273,7 @@ def main_new_model():
logger.info("class weights: set default") logger.info("class weights: set default")
custom_class_weights = None custom_class_weights = None
logger.info("start training") logger.info("start training")
server_tr = np.stack(np_utils.to_categorical(s, 2) for s in server_windows_tr) server_tr = np.expand_dims(server_windows_tr, 2)
model.fit([domain_tr, flow_tr], model.fit([domain_tr, flow_tr],
[client_tr, server_tr], [client_tr, server_tr],
batch_size=args.batch_size, batch_size=args.batch_size,

View File

@ -43,7 +43,6 @@ def get_model(cnnDropout, flow_features, domain_features, window_size, domain_le
ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows") ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
merged = keras.layers.concatenate([encoded, ipt_flows], -1) merged = keras.layers.concatenate([encoded, ipt_flows], -1)
# CNN processing a small slides of flow windows # CNN processing a small slides of flow windows
# TODO: add more layers?
y = Conv1D(cnn_dims, y = Conv1D(cnn_dims,
kernel_size, kernel_size,
activation='relu', activation='relu',
@ -52,8 +51,8 @@ def get_model(cnnDropout, flow_features, domain_features, window_size, domain_le
y = GlobalMaxPooling1D()(y) y = GlobalMaxPooling1D()(y)
y = Dropout(cnnDropout)(y) y = Dropout(cnnDropout)(y)
y = Dense(dense_dim, activation='relu')(y) y = Dense(dense_dim, activation='relu')(y)
y1 = Dense(2, activation='softmax', name="client")(y) y1 = Dense(1, activation='sigmoid', name="client")(y)
y2 = Dense(2, activation='softmax', name="server")(y) y2 = Dense(1, activation='sigmoid', name="server")(y)
return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2)) return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))
@ -64,7 +63,7 @@ def get_new_model(dropout, flow_features, domain_features, window_size, domain_l
ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows") ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
encoded = TimeDistributed(cnn)(ipt_domains) encoded = TimeDistributed(cnn)(ipt_domains)
y2 = Dense(2, activation="softmax", name="server")(encoded) y2 = Dense(1, activation="sigmoid", name="server")(encoded)
merged = keras.layers.concatenate([encoded, ipt_flows, y2], -1) merged = keras.layers.concatenate([encoded, ipt_flows, y2], -1)
y = Conv1D(cnn_dims, y = Conv1D(cnn_dims,
@ -76,7 +75,7 @@ def get_new_model(dropout, flow_features, domain_features, window_size, domain_l
y = Dropout(dropout)(y) y = Dropout(dropout)(y)
y = Dense(dense_dim, activation='relu')(y) y = Dense(dense_dim, activation='relu')(y)
y1 = Dense(2, activation='softmax', name="client")(y) y1 = Dense(1, activation='sigmoid', name="client")(y)
model = Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2)) model = Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))
return model return model

View File

@ -9,13 +9,9 @@ def get_embedding(vocab_size, embedding_size, input_length,
x = y = Input(shape=(input_length,)) x = y = Input(shape=(input_length,))
y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y) y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
y = Conv1D(filter_size, kernel_size=5, activation='relu')(y) y = Conv1D(filter_size, kernel_size=5, activation='relu')(y)
# NOTE: max pooling destroys information flow for embedding
# y = MaxPool1D(pool_size=3, strides=1)(y)
y = Conv1D(filter_size, kernel_size=3, activation='relu')(y) y = Conv1D(filter_size, kernel_size=3, activation='relu')(y)
# y = MaxPool1D(pool_size=3, strides=1)(y)
y = Conv1D(filter_size, kernel_size=3, activation='relu')(y) y = Conv1D(filter_size, kernel_size=3, activation='relu')(y)
y = GlobalAveragePooling1D()(y) y = GlobalAveragePooling1D()(y)
# y = Dropout(drop_out)(y)
y = Dense(hidden_dims, activation="relu")(y) y = Dense(hidden_dims, activation="relu")(y)
return Model(x, y) return Model(x, y)
@ -38,8 +34,8 @@ def get_model(cnnDropout, flow_features, domain_features, window_size, domain_le
y = Dropout(cnnDropout)(y) y = Dropout(cnnDropout)(y)
y = Dense(dense_dim, activation='relu')(y) y = Dense(dense_dim, activation='relu')(y)
y = Dense(dense_dim // 2, activation='relu')(y) y = Dense(dense_dim // 2, activation='relu')(y)
y1 = Dense(2, activation='softmax', name="client")(y) y1 = Dense(1, activation='sigmoid', name="client")(y)
y2 = Dense(2, activation='softmax', name="server")(y) y2 = Dense(1, activation='sigmoid', name="server")(y)
return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2)) return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))
@ -50,7 +46,7 @@ def get_new_model(dropout, flow_features, domain_features, window_size, domain_l
ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows") ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
encoded = TimeDistributed(cnn)(ipt_domains) encoded = TimeDistributed(cnn)(ipt_domains)
y2 = Dense(2, activation="softmax", name="server")(encoded) y2 = Dense(1, activation="sigmoid", name="server")(encoded)
merged = keras.layers.concatenate([encoded, ipt_flows, y2], -1) merged = keras.layers.concatenate([encoded, ipt_flows, y2], -1)
y = Conv1D(cnn_dims, y = Conv1D(cnn_dims,
@ -62,7 +58,7 @@ def get_new_model(dropout, flow_features, domain_features, window_size, domain_l
y = Dropout(dropout)(y) y = Dropout(dropout)(y)
y = Dense(dense_dim, activation='relu')(y) y = Dense(dense_dim, activation='relu')(y)
y1 = Dense(2, activation='softmax', name="client")(y) y1 = Dense(1, activation='sigmoid', name="client")(y)
model = Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2)) model = Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))
return model return model