class CometMLMonitor(MonitorBase):
"""
Send data to https://www.comet.ml.
Note:
1. comet_ml requires you to `import comet_ml` before importing tensorflow or tensorpack.
2. The "automatic output logging" feature of comet_ml will make the training progress bar appear to freeze.
Therefore the feature is disabled by default.
"""
def __init__(self, experiment=None, api_key=None, tags=None, **kwargs):
"""
Args:
experiment (comet_ml.Experiment): if provided, invalidate all other arguments
api_key (str): your comet.ml API key
tags (list[str]): experiment tags
kwargs: other arguments passed to :class:`comet_ml.Experiment`.
"""
if experiment is not None:
self._exp = experiment
assert api_key is None and tags is None and len(kwargs) == 0
else:
from comet_ml import Experiment
kwargs.setdefault(
'log_code', True
) # though it's not functioning, git patch logging requires it
kwargs.setdefault('auto_output_logging', None)
self._exp = Experiment(api_key=api_key, **kwargs)
if tags is not None:
self._exp.add_tags(tags)
self._exp.set_code(
"Code logging is impossible because there are too many files ...")
self._exp.log_dependency('tensorpack', __git_version__)
@property
def experiment(self):
"""
The :class:`comet_ml.Experiment` instance.
"""
return self._exp
def _before_train(self):
self._exp.set_model_graph(tf.get_default_graph())
@HIDE_DOC
def process_scalar(self, name, val):
self._exp.log_metric(name, val, step=self.global_step)
def _after_train(self):
self._exp.end()
def _after_epoch(self):
self._exp.log_epoch_end(self.epoch_num)
def main(cfg):
shapes = cfg.model.shapes
opt_params = cfg.optimizer.params
experiment = Experiment(log_code=False)
experiment.set_code(filename=hydra.utils.to_absolute_path(__file__))
experiment.add_tag("with_hydra")
experiment.log_parameters({"hydra-cfg": [cfg]})
model = layers.MLP(shapes)
optimizer = optim.Adam(model.parameters(), **opt_params)
runner = tasks.ClassificationRunner(
model,
optimizer=optimizer,
criterion=nn.CrossEntropyLoss(),
experiment=experiment
)
runner.fit(x, y, epochs=10, checkpoint_path="./checkpoints")
runner.save()
class CometMLLogger(Logger):
def __init__(self, logger_kwargs=None):
super().__init__(logger_kwargs=logger_kwargs)
self.experiment = Experiment(api_key=self.config["api_key"],
project_name=self.config["project_name"],
log_code=False,
log_graph=False,
auto_param_logging=False,
auto_metric_logging=False,
auto_output_logging=None,
log_env_details=False,
log_git_metadata=False)
if "reward_func" in self.config:
self.experiment.set_code(
inspect.getsource(self.config["reward_func"]))
def log_hyperparams(self, hyperparams, step=0):
self.experiment.log_multiple_params(hyperparams, step=step)
def log_metric(self, key, value, step=0):
self.experiment.log_metric(key, value, step=step)
class CometMLMonitor(MonitorBase):
"""
Send scalar data and the graph to https://www.comet.ml.
Note:
1. comet_ml requires you to `import comet_ml` before importing tensorflow or tensorpack.
2. The "automatic output logging" feature of comet_ml will make the training progress bar appear to freeze.
Therefore the feature is disabled by default.
"""
def __init__(self, experiment=None, tags=None, **kwargs):
"""
Args:
experiment (comet_ml.Experiment): if provided, invalidate all other arguments
tags (list[str]): experiment tags
kwargs: arguments used to initialize :class:`comet_ml.Experiment`,
such as project name, API key, etc.
Refer to its documentation for details.
"""
if experiment is not None:
self._exp = experiment
assert tags is None and len(kwargs) == 0
else:
from comet_ml import Experiment
kwargs.setdefault(
'log_code', True
) # though it's not functioning, git patch logging requires it
kwargs.setdefault('auto_output_logging', None)
self._exp = Experiment(**kwargs)
if tags is not None:
self._exp.add_tags(tags)
self._exp.set_code("Code logging is impossible ...")
self._exp.log_dependency('tensorpack', __git_version__)
@property
def experiment(self):
"""
The :class:`comet_ml.Experiment` instance.
"""
return self._exp
def _before_train(self):
self._exp.set_model_graph(tf.get_default_graph())
@HIDE_DOC
def process_scalar(self, name, val):
self._exp.log_metric(name, val, step=self.global_step)
@HIDE_DOC
def process_image(self, name, val):
self._exp.set_step(self.global_step)
for idx, v in enumerate(val):
log_name = "{}_step{}{}".format(
name, self.global_step, "_" + str(idx) if len(val) > 1 else "")
self._exp.log_image(v,
image_format="jpeg",
name=log_name,
image_minmax=(0, 255))
def _after_train(self):
self._exp.end()
def _after_epoch(self):
self._exp.log_epoch_end(self.epoch_num)
epochs = 100000
steps_per_epoch = 0
total_images_looked_at = 0
d_steps = 1
g_steps = 1
graph, iterator, d_train_optimizer_ops, d_stabilize_optimizer_ops, g_train_optimizer_ops, g_stabilize_optimizer_ops, samples_for_all_resolutions, sizes = model.get_graph()
experiment = Experiment(api_key='<API_KEY>', project_name='art_pgan', workspace='schmidtdominik', log_code=False)
experiment.log_parameters({'G_learning_rate': model.g_learning_rate, 'D_learning_rate': model.d_learning_rate, 'D_steps': d_steps, 'G_steps': g_steps, 'batch_size': model.batch_size})
experiment.set_model_graph(graph)
experiment.set_code('\n# [code]: train.py\n' + open('train.py', 'r').read() + '\n# [code]: image_pipeline.py\n' + open('image_pipeline.py', 'r').read() + '\n# [code]: model.py\n' + open(
'model.py', 'r').read() + '\n# [code]: discriminator.py\n' + open('discriminator.py', 'r').read() + '\n# [code]: generator.py\n' + open(
'generator.py', 'r').read())
try: os.mkdir('./checkpoints/')
except FileExistsError: pass
try: os.mkdir('./progress_images/')
except FileExistsError: pass
current_resolution = sizes[0]
current_mode = 'train'
last_schedule_update = 0
last_schedule_update_time = time.time()
schedule_finalized = False
# T4 --> S8 --> T8 --> S16 --> T16 --> ...
model_params = json.load(json_file)
with open('main.py', 'r') as file:
code = file.read()
parameters = {
k: model_params[args.model][k]
for k in ('population', 'generations', 'crossover', 'factor')
}
experiment = Experiment(api_key=os.environ['COMET_API'],
project_name=os.environ['PROJECT_NAME'],
log_code=False,
auto_param_logging=False)
experiment.add_tag(args.model)
experiment.set_code(code=code, overwrite=True)
experiment.log_parameters(parameters)
proc = subprocess.Popen(
"python main.py --np %s --max_gen %s --cr %s --f %s" % (
parameters['population'],
parameters['generations'],
parameters['crossover'],
parameters['factor'],
),
stdout=subprocess.PIPE,
shell=True)
output = proc.stdout.read()
scrap_output(output.decode("utf-8"),
if args.comet is not None:
experiment = Experiment(api_key=args.comet,
workspace=args.workspace,
project_name=args.project,
parse_args=False,
auto_output_logging=None)
if args.tags:
experiment.add_tags(args.tags)
with open(args.param_path) as fil:
code = "".join(fil.readlines())
code += "\n\n#=============Full details=============\n\n"
code += _jsonnet.evaluate_file(args.param_path)
code += "\n\n#=============IMPORTANT: overwritten options============\n\n"
code += args.overrides
experiment.set_code(code)
code_data = json.loads(_jsonnet.evaluate_file(args.param_path))
experiment.log_parameter(
"bert", "bert" in code_data["dataset_reader"]["token_indexers"])
experiment.log_parameter(
"elmo", "elmo" in code_data["dataset_reader"]["token_indexers"])
experiment.log_parameter("model_directory", serialization_dir)
experiment.log_parameter("cuda_device", cuda_device)
experiment.log_parameter("corpora", code_data["iterator"]["formalisms"])
experiment.log_parameter("encoder", code_data["model"]["encoder"]["type"])
experiment.log_parameter("hostname", socket.gethostname())
experiment.log_parameter(
"random_seed", random_seed) #random_seed, numpy_seed, pytorch_seed
experiment.log_parameter(
"numpy_seed", numpy_seed) #random_seed, numpy_seed, pytorch_seed
experiment.log_parameter(
def main(args: argparse.Namespace):
for package_name in args.include_package:
import_module_and_submodules(package_name)
params = Params.from_file(args.param_path, args.overrides)
random_seed, numpy_seed, pytorch_seed = 41, 11, 302
if not args.fix:
random_seed, numpy_seed, pytorch_seed = random.randint(
0, 999999999), random.randint(0, 999999999), random.randint(
0, 999999999)
params["random_seed"] = random_seed
params["numpy_seed"] = numpy_seed
params["pytorch_seed"] = pytorch_seed
prepare_environment(params)
serialization_dir = args.serialization_dir
create_serialization_dir(params, serialization_dir, args.recover,
args.force)
prepare_global_logging(serialization_dir, args.file_friendly_logging)
hyperparams = list(
get_hyperparams(params.as_dict(infer_type_and_cast=True)))
params.to_file(os.path.join(serialization_dir, CONFIG_NAME))
test_file = params.params.get("test_data_path", None)
validation_data_path = params.get("validation_data_path", None)
evaluate_on_test = params.pop_bool("evaluate_on_test", False)
test_command = None
if evaluate_on_test:
test_command = BaseEvaluationCommand.from_params(
params.pop("test_command"))
cuda_device = params.params.get('trainer').get('cuda_device', -1)
check_for_gpu(cuda_device)
train_model = TrainPipelineModel.from_params(
params=params, serialization_dir=serialization_dir, local_rank=0)
trainer = train_model.trainer
if trainer.validation_command is not None:
trainer.validation_command.maybe_set_gold_file(validation_data_path)
params.assert_empty('base train command')
if args.comet is not None:
experiment = Experiment(api_key=args.comet,
workspace=args.workspace,
project_name=args.project,
parse_args=False,
auto_output_logging=None)
if args.tags:
experiment.add_tags(args.tags)
with open(args.param_path) as fil:
code = "".join(fil.readlines())
code += "\n\n#=============Full details=============\n\n"
full_details = _jsonnet.evaluate_file(args.param_path)
code += full_details
code += "\n\n#=============IMPORTANT: overwritten options============\n\n"
code += args.overrides
experiment.set_code(code, overwrite=True)
for key, val in hyperparams:
experiment.log_parameter(key, val)
experiment.log_parameter("model_directory", serialization_dir)
experiment.log_parameter("cuda_device", cuda_device)
experiment.log_parameter("hostname", socket.gethostname())
experiment.log_parameter("random_seed", random_seed)
experiment.log_parameter("numpy_seed", numpy_seed)
experiment.log_parameter("pytorch_seed", pytorch_seed)
else:
experiment = None
try:
metrics = trainer.train(experiment)
except KeyboardInterrupt:
# if we have completed an epoch, try to create a model archive.
if os.path.exists(os.path.join(serialization_dir, _DEFAULT_WEIGHTS)):
logging.info(
"Training interrupted by the user. Attempting to create "
"a model archive using the current best epoch weights.")
archive_model(serialization_dir)
raise
# Evaluate
if test_file and evaluate_on_test:
logger.info(
"The model will be evaluated using the best epoch weights (see pred_test.txt)."
)
trainer.annotator.annotate_file(
trainer.model, test_file,
os.path.join(serialization_dir, "pred_test.txt"))
if test_command:
logger.info("Comparing against gold standard.")
test_command.maybe_set_gold_file(test_file)
test_metrics = test_command.evaluate(
os.path.join(serialization_dir, "pred_test.txt"))
if experiment:
with experiment.test():
experiment.log_metrics({
k: v
for k, v in test_metrics.items() if np.isscalar(v)
})
metrics = merge_dicts(metrics, "test", test_metrics)
dump_metrics(os.path.join(serialization_dir, "metrics.json"),
metrics,
log=True)
if not args.no_archive:
# Now tar up results
archive_model(serialization_dir)
