#### norm the data ####
data_utils.norm_data(test_x, inp_scaler)
#### compute predictions ####
keras_models.predict(test_x, out_scaler, gen_test_file_list, cfg.sequential_training)
if __name__ == "__main__":
if len(sys.argv) != 2:
logger.critical('usage: python run_keras_with_merlin_io.py [config file name]')
sys.exit(1)
# create a configuration instance
# and get a short name for this instance
cfg = configuration.configuration()
config_file = sys.argv[1]
config_file = os.path.abspath(config_file)
cfg.configure(config_file)
print("--- Job started ---")
start_time = time.time()
# main function
main(cfg)
(m, s) = divmod(int(time.time() - start_time), 60)
print("--- Job completion time: %d min. %d sec ---" % (m, s))
if self.TRAINMODEL:
self.train_keras_model()
if self.TESTMODEL:
self.test_keras_model()
if __name__ == "__main__":
if len(sys.argv) != 2:
print('usage: python run_keras_with_merlin_io.py [config file name]')
sys.exit(1)
# create a configuration instance
# and get a short name for this instance
cfg = configuration.configuration()
config_file = sys.argv[1]
config_file = os.path.abspath(config_file)
cfg.configure(config_file)
print("--- Job started ---")
start_time = time.time()
# main function
keras_instance = KerasClass(cfg)
keras_instance.main_function()
(m, s) = divmod(int(time.time() - start_time), 60)
print(("--- Job completion time: %d min. %d sec ---" % (m, s)))