def model_train_small(model_type='fc'):
"""
Use for fast iteration
:param model_type:
:return:
"""
start = timer()
if model_type == 'fc':
model_pair = build_fc_network()
elif model_type == 'cnn':
model_pair = build_cnn_network()
else:
print("Type not supported")
return
end = timer()
print("{} min taken for generating networks".format((end - start) / 60.0))
start = timer()
train_file_list = fetch_file_list(data_dir=TRAINING_DATA_DIR, portion=1.1)
tg = build_numpy(file_list=train_file_list, num_samples=None, xcolumns=X_COLUMNS,
ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
val_file_list = fetch_file_list(data_dir=VALIDATION_DATA_DIR, portion=1.1)
vg = build_numpy(file_list=val_file_list, num_samples=None, xcolumns=X_COLUMNS,
ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
end = timer()
print("{} min taken for generating input".format((end - start) / 60.0))
count = np.sum(tg[1], axis=0)
print("Number of Positive Training Windows: {}".format(count[0]))
print("Number of Negative Training Windows: {}".format(len(tg[1]) - count[0]))
key = model_pair[0] + '_small'
model = model_pair[1]
print(key)
print(model.summary())
file_path = MODEL_CHECKPOINT + key + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
history = History()
log_dir = LOG_DIR + key + '/' + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensor_board = TensorBoard(log_dir, histogram_freq=5,
write_grads=False, write_graph=False)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5,
patience=4, min_lr=1e-5)
checkpoint = ModelCheckpoint(file_path, monitor='val_loss', verbose=1, save_best_only=True, mode='min', period=5)
callbacks_list = [history, tensor_board, reduce_lr, checkpoint]
adam_wn = Adam(lr=LR)
model.compile(loss="sparse_categorical_crossentropy", optimizer=adam_wn, metrics=['accuracy'])
model.fit(x=tg[0], y=tg[1], validation_data=vg, batch_size=BATCH_SIZE,
epochs=EPOCHS, verbose=1, shuffle=False,
callbacks=callbacks_list, class_weight={0: 0.1, 1: 1.0})
model.save(file_path)
return
def model_train(model_type='fc'):
"""
Use for fast iteration
:param model_type:
:return:
"""
start = timer()
if model_type == 'fc':
model_pair = build_fc_network()
elif model_type == 'cnn':
model_pair = build_cnn_network()
else:
print("Type not supported")
return
end = timer()
print("{} min taken for generating networks".format((end - start) / 60.0))
start = timer()
train_file_list = fetch_file_list(data_dir=TRAINING_DATA_DIR, portion=TRAIN_PORTION)
tg = build_generator(file_list=train_file_list, xcolumns=X_COLUMNS, ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
v_file_list = fetch_file_list(data_dir=VALIDATION_DATA_DIR, portion=VALIDATION_PORTION)
vg = build_generator(file_list=v_file_list, xcolumns=X_COLUMNS, ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
end = timer()
print("{} min taken for generating input".format((end - start) / 60.0))
key = model_pair[0]
model = model_pair[1]
print(key)
print(model.summary())
history = History()
log_dir = LOG_DIR + key + '/' + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
file_path = MODEL_CHECKPOINT + key + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensor_board = TensorBoard(log_dir, histogram_freq=5,
write_grads=False, write_graph=False, profile_batch=0)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5,
patience=4, min_lr=1e-5)
checkpoint = ModelCheckpoint(file_path, monitor='val_loss', verbose=1, save_best_only=True, mode='min', period=5)
callbacks_list = [history, tensor_board, reduce_lr, checkpoint]
adam_wn = Adam(lr=LR)
model.compile(loss="sparse_categorical_crossentropy", optimizer=adam_wn, metrics=['accuracy'])
model.fit_generator(generator=tg, steps_per_epoch=int(NUM_TRAIN_SAMPLES/BATCH_SIZE),
epochs=EPOCHS, verbose=1, shuffle=True,
use_multiprocessing=True, workers=10,
callbacks=callbacks_list,
max_queue_size=len(train_file_list),
validation_data=vg, validation_steps=int(NUM_VALI_SAMPLES/BATCH_SIZE),
class_weight={0: 0.1, 1: 1.0})
model.save(file_path)
return
def model_train_resume(model_path):
"""
Resume training a saved model
:param model_path:
:return:
"""
# load model
model = load_model(model_path)
start = timer()
train_file_list = fetch_file_list(data_dir=TRAINING_DATA_DIR, portion=TRAIN_PORTION)
tg = build_generator(file_list=train_file_list, xcolumns=X_COLUMNS, ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
v_file_list = fetch_file_list(data_dir=VALIDATION_DATA_DIR, portion=VALIDATION_PORTION)
vg = build_generator(file_list=v_file_list, xcolumns=X_COLUMNS, ycolumns=Y_COLUMNS, ytx=None, is_csv=IS_CSV)
end = timer()
print("{} min taken for generating input".format((end - start) / 60.0))
print(model_path)
print(model.summary())
new_path = model_path + '_resume_{}'.format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
checkpoint = ModelCheckpoint(new_path, monitor='val_loss', verbose=1, save_best_only=True, mode='min', period=5)
history = History()
log_dir = LOG_DIR + model_path.split('/')[-1] \
+ '_resume_{}'.format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
tensor_board = TensorBoard(log_dir, histogram_freq=1)
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5,
patience=3, min_lr=1e-5)
callbacks_list = [history, tensor_board, checkpoint, reduce_lr]
# hack!!!
print(K.eval(model.optimizer.lr))
adam_wn = Adam(lr=LR)
model.compile(loss="sparse_categorical_crossentropy", optimizer=adam_wn, metrics=['accuracy'])
print(K.eval(model.optimizer.lr))
model.fit_generator(generator=tg, steps_per_epoch=int(NUM_TRAIN_SAMPLES/BATCH_SIZE),
epochs=EPOCHS, verbose=1, shuffle=True,
use_multiprocessing=True, workers=10,
callbacks=callbacks_list,
max_queue_size=len(train_file_list),
validation_data=vg, validation_steps=int(NUM_VALI_SAMPLES/BATCH_SIZE),
class_weight={0: 0.1, 1: 1.0})
model.save(new_path)
return
def xgboost_train():
train_file_list = fetch_file_list(data_dir=TRAINING_DATA_DIR, portion=1)
tg = build_numpy(file_list=train_file_list,
num_samples=None,
xcolumns=X_COLUMNS,
ycolumns=Y_COLUMNS,
ytx=None,
skip_header=1,
shuffle=False,
is_csv=IS_CSV)
val_file_list = fetch_file_list(data_dir=VALIDATION_DATA_DIR, portion=1)
vg = build_numpy(file_list=val_file_list,
num_samples=None,
xcolumns=X_COLUMNS,
ycolumns=Y_COLUMNS,
ytx=None,
skip_header=1,
shuffle=False,
is_csv=IS_CSV)
x_train = copy.deepcopy(tg[0])
y_train = copy.deepcopy(tg[1].reshape(-1))
x_val = copy.deepcopy(vg[0])
y_val = copy.deepcopy(vg[1].reshape(-1))
del tg
del vg
count = np.sum(y_train)
print("Number of Positive Training Windows: {}".format(count))
print(
"Number of Negative Training Windows: {}".format(len(y_train) - count))
eval_set = [(x_train, y_train), (x_val, y_val)]
my_model = XGBClassifier(base_score=0.5,
booster='gbtree',
colsample_by_level=1,
colsample_bynode=1,
colsample_bytree=0.8,
eta=0.03,
gamma=0.1,
learning_rate=0.1,
ax_delta_step=0,
max_depth=6,
min_child_weight=3,
missing=None,
n_estimators=600,
n_jobs=1,
nthread=None,
objective='binary:logistic',
random_state=0,
reg_alpha=0,
reg_lambda=1,
scale_pos_weight=XGBOOST_POSITIVE_WEIGHT,
seed=1234,
subsample=0.8,
verbosity=2,
tree_method='hist')
my_model.get_xgb_params()
# logloss here equivalent to CategoricalCrossEntropy in tensorflow
trained = my_model.fit(x_train,
y_train,
early_stopping_rounds=15,
eval_metric=["logloss", "error"],
eval_set=eval_set,
verbose=True)
key = "xgboost-withClassWeight"
file_path = MODEL_CHECKPOINT + key + datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S")
trained.save_model(file_path)
return trained