class CometWriter:
def __init__(self,
logger,
project_name: Optional[str] = None,
experiment_name: Optional[str] = None,
api_key: Optional[str] = None,
log_dir: Optional[str] = None,
offline: bool = False,
**kwargs):
if not _COMET_AVAILABLE:
raise ImportError(
"You want to use `comet_ml` logger which is not installed yet,"
" install it with `pip install comet-ml`.")
self.project_name = project_name
self.experiment_name = experiment_name
self.kwargs = kwargs
self.timer = Timer()
if (api_key is not None) and (log_dir is not None):
self.mode = "offline" if offline else "online"
self.api_key = api_key
self.log_dir = log_dir
elif api_key is not None:
self.mode = "online"
self.api_key = api_key
self.log_dir = None
elif log_dir is not None:
self.mode = "offline"
self.log_dir = log_dir
else:
logger.warning(
"CometLogger requires either api_key or save_dir during initialization."
)
if self.mode == "online":
self.experiment = CometExperiment(
api_key=self.api_key,
project_name=self.project_name,
**self.kwargs,
)
else:
self.experiment = CometOfflineExperiment(
offline_directory=self.log_dir,
project_name=self.project_name,
**self.kwargs,
)
if self.experiment_name:
self.experiment.set_name(self.experiment_name)
def set_step(self, step, epoch=None, mode='train') -> None:
self.mode = mode
self.step = step
self.epoch = epoch
if step == 0:
self.timer.reset()
else:
duration = self.timer.check()
self.add_scalar({'steps_per_sec': 1 / duration})
def log_hyperparams(self, params: Dict[str, Any]) -> None:
self.experiment.log_parameters(params)
def log_code(self, file_name=None, folder='models/') -> None:
self.experiment.log_code(file_name=file_name, folder=folder)
def add_scalar(self,
metrics: Dict[str, Union[torch.Tensor, float]],
step: Optional[int] = None,
epoch: Optional[int] = None) -> None:
metrics_renamed = {}
for key, val in metrics.items():
tag = '{}/{}'.format(key, self.mode)
if is_tensor(val):
metrics_renamed[tag] = val.cpu().detach()
else:
metrics_renamed[tag] = val
if epoch is None:
self.experiment.log_metrics(metrics_renamed,
step=self.step,
epoch=self.epoch)
else:
self.experiment.log_metrics(metrics_renamed, epoch=epoch)
def add_plot(self, figure_name, figure):
"""
Primarily for log gate plots
"""
self.experiment.log_figure(figure_name=figure_name, figure=figure)
def add_hist3d(self, hist, name):
"""
Primarily for log gate plots
"""
self.experiment.log_histogram_3d(hist, name=name)
def reset_experiment(self):
self.experiment = None
def finalize(self) -> None:
self.experiment.end()
self.reset_experiment()
def train(config, weights, ntrain, ntest, nepochs, recreate, prefix, plot_freq,
customize, comet_offline):
# tf.debugging.enable_check_numerics()
"""Train a model defined by config"""
config_file_path = config
config, config_file_stem = parse_config(config,
nepochs=nepochs,
weights=weights)
if plot_freq:
config["callbacks"]["plot_freq"] = plot_freq
if customize:
config = customization_functions[customize](config)
# Decide tf.distribute.strategy depending on number of available GPUs
horovod_enabled = config["setup"]["horovod_enabled"]
if horovod_enabled:
num_gpus = initialize_horovod()
else:
strategy, num_gpus = get_strategy()
outdir = ""
if not horovod_enabled or hvd.rank() == 0:
outdir = create_experiment_dir(prefix=prefix + config_file_stem + "_",
suffix=platform.node())
shutil.copy(
config_file_path, outdir + "/config.yaml"
) # Copy the config file to the train dir for later reference
try:
if comet_offline:
print("Using comet-ml OfflineExperiment, saving logs locally.")
from comet_ml import OfflineExperiment
experiment = OfflineExperiment(
project_name="particleflow-tf",
auto_metric_logging=True,
auto_param_logging=True,
auto_histogram_weight_logging=True,
auto_histogram_gradient_logging=False,
auto_histogram_activation_logging=False,
offline_directory=outdir + "/cometml",
)
else:
print("Using comet-ml Experiment, streaming logs to www.comet.ml.")
from comet_ml import Experiment
experiment = Experiment(
project_name="particleflow-tf",
auto_metric_logging=True,
auto_param_logging=True,
auto_histogram_weight_logging=True,
auto_histogram_gradient_logging=False,
auto_histogram_activation_logging=False,
)
except Exception as e:
print("Failed to initialize comet-ml dashboard: {}".format(e))
experiment = None
if experiment:
experiment.set_name(outdir)
experiment.log_code("mlpf/tfmodel/model.py")
experiment.log_code("mlpf/tfmodel/utils.py")
experiment.log_code(config_file_path)
ds_train, num_train_steps = get_datasets(config["train_test_datasets"],
config, num_gpus, "train")
ds_test, num_test_steps = get_datasets(config["train_test_datasets"],
config, num_gpus, "test")
ds_val, ds_info = get_heptfds_dataset(
config["validation_datasets"][0],
config,
num_gpus,
"test",
config["setup"]["num_events_validation"],
supervised=False,
)
ds_val = ds_val.batch(5)
if ntrain:
ds_train = ds_train.take(ntrain)
num_train_steps = ntrain
if ntest:
ds_test = ds_test.take(ntest)
num_test_steps = ntest
print("num_train_steps", num_train_steps)
print("num_test_steps", num_test_steps)
total_steps = num_train_steps * config["setup"]["num_epochs"]
print("total_steps", total_steps)
if horovod_enabled:
model, optim_callbacks, initial_epoch = model_scope(
config, total_steps, weights, horovod_enabled)
else:
with strategy.scope():
model, optim_callbacks, initial_epoch = model_scope(
config, total_steps, weights)
callbacks = prepare_callbacks(
config,
outdir,
ds_val,
comet_experiment=experiment,
horovod_enabled=config["setup"]["horovod_enabled"])
verbose = 1
if horovod_enabled:
callbacks.append(hvd.callbacks.BroadcastGlobalVariablesCallback(0))
callbacks.append(hvd.callbacks.MetricAverageCallback())
verbose = 1 if hvd.rank() == 0 else 0
num_train_steps /= hvd.size()
num_test_steps /= hvd.size()
callbacks.append(optim_callbacks)
model.fit(
ds_train.repeat(),
validation_data=ds_test.repeat(),
epochs=initial_epoch + config["setup"]["num_epochs"],
callbacks=callbacks,
steps_per_epoch=num_train_steps,
validation_steps=num_test_steps,
initial_epoch=initial_epoch,
verbose=verbose,
)
