discretizer,
normalizer,
args.batch_size,
args.small_part,
target_repl,
shuffle=False)
if args.mode == 'train':
# Prepare training
path = os.path.join(
args.output_dir, 'keras_states/' + model.final_name +
'.epoch{epoch}.test{val_loss}.state')
metrics_callback = keras_utils.PhenotypingMetrics(
train_data_gen=train_data_gen,
val_data_gen=val_data_gen,
batch_size=args.batch_size,
verbose=args.verbose)
# make sure save directory exists
dirname = os.path.dirname(path)
if not os.path.exists(dirname):
os.makedirs(dirname)
saver = ModelCheckpoint(path, verbose=1, period=args.save_every)
keras_logs = os.path.join(args.output_dir, 'keras_logs')
if not os.path.exists(keras_logs):
os.makedirs(keras_logs)
csv_logger = CSVLogger(os.path.join(keras_logs, model.final_name + '.csv'),
append=True,
separator=';')
normalizer,
args.batch_size,
args.small_part,
target_repl,
shuffle=False)
if args.mode == 'train':
# Prepare training
path = os.path.join(
args.output_dir, 'keras_states/' + model.final_name +
'.epoch{epoch}.test{val_loss}.state')
metrics_callback = keras_utils.PhenotypingMetrics(
train_data_gen=train_data_gen,
val_data_gen=val_data_gen,
delta=1e-7,
batch_size=args.batch_size,
verbose=args.verbose,
dp=args.dp,
noise_multiplier=args.noise_multiplier)
# make sure save directory exists
dirname = os.path.dirname(path)
if not os.path.exists(dirname):
os.makedirs(dirname)
saver = ModelCheckpoint(path, verbose=1, period=args.save_every)
keras_logs = os.path.join(args.output_dir, 'keras_logs')
if not os.path.exists(keras_logs):
os.makedirs(keras_logs)
csv_logger = CSVLogger(os.path.join(keras_logs, model.final_name + '.csv'),
append=True,
separator=';')