def test_create_all_services(artifact_dir):
cfg_services = {
"best_checkpoint": {
"monitor": "val_loss",
"mode": "min"
},
"tensorboard": {},
"train_early_stopping": {
"monitor": "loss",
"mode": "min",
"patience": 2,
"min_delta": 1e-2,
"verbose": 0,
},
"validation_early_stopping": {
"monitor": "val_loss",
"mode": "min",
"patience": 2,
"min_delta": 1e-2,
},
}
metrics_names = ["loss"]
result = services.create_all_services(artifact_dir, cfg_services,
metrics_names)
assert isinstance(result[0], tf.keras.callbacks.ModelCheckpoint)
assert isinstance(result[1], tf.keras.callbacks.ModelCheckpoint)
assert isinstance(result[2], tf.keras.callbacks.TensorBoard)
assert isinstance(result[3], tf.keras.callbacks.CSVLogger)
assert isinstance(result[4], tf.keras.callbacks.EarlyStopping)
assert isinstance(result[5], tf.keras.callbacks.EarlyStopping)
assert isinstance(result[6], tf.keras.callbacks.TerminateOnNaN)
def train(
self,
cfg: dict,
records_train: api.InputRecords,
records_validation: api.InputRecords,
) -> tf.keras.Model:
"""Train the network.
Args:
cfg: dict, config.
records_train: InputRecords, training records.
records_validation: InputRecords, validation records.
Returns:
tf.keras.Model, trained network.
"""
logger.info("Starting training")
tf_utils.reset()
cfg = config.prepare_config(cfg)
logger.info(f"Creating artifact directory: {self.artifact_dir}")
services.make_artifact_dir(self.artifact_dir)
io_utils.save_json(cfg, "config.json", self.artifact_dir)
io_utils.save_pickle(cfg, "config.pkl", self.artifact_dir)
logger.info("Creating datasets")
ds_train = dataset.RecordDataset(
artifact_dir=self.artifact_dir,
cfg_dataset=cfg["dataset"],
records=records_train,
mode=api.RecordMode.TRAIN,
batch_size=cfg["solver"]["batch_size"],
)
ds_validation = dataset.RecordDataset(
artifact_dir=self.artifact_dir,
cfg_dataset=cfg["dataset"],
records=records_validation,
mode=api.RecordMode.VALIDATION,
batch_size=cfg["solver"]["batch_size"],
)
network_params = ds_train.transformer.network_params
io_utils.save_json(network_params, "network_params.json", self.artifact_dir)
io_utils.save_pickle(network_params, "network_params.pkl", self.artifact_dir)
logger.info("Building network")
net = model.build_network(cfg["model"], network_params)
model.check_output_names(cfg["model"], net)
logger.info("Compiling network")
opt = solver.build_optimizer(cfg["solver"])
objective = model.build_objective(cfg["model"])
net.compile(optimizer=opt, **objective)
logger.info("Creating services")
callbacks = services.create_all_services(self.artifact_dir, cfg["services"])
if "learning_rate_reducer" in cfg["solver"]:
logger.info("Creating learning rate reducer")
callbacks.append(solver.create_learning_rate_reducer(cfg["solver"]))
logger.info("Training network")
net.summary()
net.fit(
ds_train,
validation_data=ds_validation,
epochs=cfg["solver"]["epochs"],
steps_per_epoch=cfg["solver"].get("steps"),
callbacks=callbacks,
verbose=1,
)
return net
def train(
self,
cfg: dict,
records_train: Union[pd.DataFrame, api.Records],
records_validation: Union[pd.DataFrame, api.Records],
workers: int = 10,
max_queue_size: int = 10,
) -> tf.keras.Model:
"""Train the network.
Args:
cfg: dict, config.
records_train: Union[pd.DataFrame, Records], training records.
records_validation: Union[pd.DataFrame, Records], validation records.
workers: int (OPTIONAL = 10), number of process threads for the sequence.
max_queue_size: int (OPTIONAL = 10), queue size for the sequence.
Returns:
tf.keras.Model, trained network.
"""
logger.info("Starting training")
tf_utils.reset()
logger.info("Validating config schema and applying defaults")
cfg = config.prepare_config(cfg)
logger.info(f"Making artifact directory: {self._artifact_dir}")
services.make_artifact_dir(self._artifact_dir)
logger.info("Saving config")
io_utils.save_json(cfg, "config.json", self._artifact_dir)
io_utils.save_pickle(cfg, "config.pkl", self._artifact_dir)
logger.info("Building datasets")
ds_train = dataset.RecordDataset(
artifact_dir=self._artifact_dir,
cfg_dataset=cfg["dataset"],
records=records_train,
mode=api.RecordMode.TRAIN,
batch_size=cfg["solver"]["batch_size"],
)
ds_validation = dataset.RecordDataset(
artifact_dir=self._artifact_dir,
cfg_dataset=cfg["dataset"],
records=records_validation,
mode=api.RecordMode.VALIDATION,
batch_size=cfg["solver"]["batch_size"],
)
network_params = ds_train.transformer.network_params
io_utils.save_json(network_params, "network_params.json", self._artifact_dir)
io_utils.save_pickle(network_params, "network_params.pkl", self._artifact_dir)
logger.info("Building network")
net = model.build_network(cfg["model"], network_params)
logger.info("Checking network output names match config output names")
model.check_output_names(cfg["model"], net)
logger.info("Building optimizer")
opt = solver.build_optimizer(cfg["solver"])
logger.info("Building objective")
objective = model.build_objective(cfg["model"])
logger.info("Compiling network")
net.compile(optimizer=opt, **objective)
metrics_names = net.metrics_names
logger.info("Creating services")
callbacks = services.create_all_services(
self._artifact_dir, cfg["services"], metrics_names
)
if "learning_rate_reducer" in cfg["solver"]:
logger.info("Creating learning rate reducer")
callbacks.append(
solver.create_learning_rate_reducer(cfg["solver"], metrics_names)
)
logger.info("Training network")
logger.info(net.summary())
net.fit_generator(
ds_train,
validation_data=ds_validation,
epochs=cfg["solver"]["epochs"],
steps_per_epoch=cfg["solver"].get("steps"),
callbacks=callbacks,
use_multiprocessing=(workers > 1),
max_queue_size=max_queue_size,
workers=workers,
verbose=1,
)
return net