def main():
args = parser.parse_args()
pipeline_config_path = find_config(args.config_path)
key_main_model = args.key_main_model
population_size = args.p_size
gpus = [int(gpu) for gpu in args.gpus.split(",")]
train_partition = int(args.train_partition)
start_from_population = int(args.start_from_population)
path_to_population = args.path_to_population
elitism_with_weights = args.elitism_with_weights
iterations = int(args.iterations)
p_crossover = args.p_cross
pow_crossover = args.pow_cross
p_mutation = args.p_mut
pow_mutation = args.pow_mut
if os.environ.get("CUDA_VISIBLE_DEVICES") is None:
pass
else:
cvd = [
int(gpu)
for gpu in os.environ.get("CUDA_VISIBLE_DEVICES").split(",")
]
if gpus == [-1]:
gpus = cvd
else:
try:
gpus = [cvd[gpu] for gpu in gpus]
except IndexError:
raise ConfigError(
"Can not use gpus `{}` with CUDA_VISIBLE_DEVICES='{}'".
format(",".join(map(str, gpus)), ",".join(map(str, cvd))))
basic_params = read_json(pipeline_config_path)
log.info("Given basic params: {}\n".format(
json.dumps(basic_params, indent=2)))
# Initialize evolution
evolution = ParamsEvolution(population_size=population_size,
p_crossover=p_crossover,
crossover_power=pow_crossover,
p_mutation=p_mutation,
mutation_power=pow_mutation,
key_main_model=key_main_model,
seed=42,
train_partition=train_partition,
elitism_with_weights=elitism_with_weights,
**basic_params)
considered_metrics = evolution.get_value_from_config(
evolution.basic_config,
list(evolution.find_model_path(evolution.basic_config, "metrics"))[0] +
["metrics"])
considered_metrics = [
metric['name'] if isinstance(metric, dict) else metric
for metric in considered_metrics
]
log.info(considered_metrics)
evolve_metric = considered_metrics[0]
# Create table variable for gathering results
abs_path_to_main_models = expand_path(
parse_value_with_config(evolution.models_path, evolution.basic_config))
abs_path_to_main_models.mkdir(parents=True, exist_ok=True)
result_file = abs_path_to_main_models / "result_table.tsv"
print(result_file)
result_table_columns = []
result_table_dict = {}
for el in considered_metrics:
result_table_dict[el + "_valid"] = []
result_table_dict[el + "_test"] = []
result_table_columns.extend([el + "_valid", el + "_test"])
result_table_dict["params"] = []
result_table_columns.append("params")
if start_from_population == 0:
# if starting evolution from scratch
iters = 0
result_table = pd.DataFrame(result_table_dict)
# write down result table file
result_table.loc[:, result_table_columns].to_csv(result_file,
index=False,
sep='\t')
log.info("Iteration #{} starts".format(iters))
# randomly generate the first population
population = evolution.first_generation()
else:
# if starting evolution from already existing population
iters = start_from_population
log.info("Iteration #{} starts".format(iters))
population = []
for i in range(population_size):
config = read_json(
expand_path(path_to_population) / f"model_{i}" / "config.json")
evolution.insert_value_or_dict_into_config(
config, evolution.path_to_models_save_path,
str(evolution.main_model_path /
f"population_{start_from_population}" / f"model_{i}"))
population.append(config)
run_population(population, evolution, gpus)
population_scores = results_to_table(population, evolution,
considered_metrics, result_file,
result_table_columns)[evolve_metric]
log.info("Population scores: {}".format(population_scores))
log.info("Iteration #{} was done".format(iters))
iters += 1
while True:
if iterations != -1 and start_from_population + iterations == iters:
log.info("End of evolution on iteration #{}".format(iters))
break
log.info("Iteration #{} starts".format(iters))
population = evolution.next_generation(population, population_scores,
iters)
run_population(population, evolution, gpus)
population_scores = results_to_table(
population, evolution, considered_metrics, result_file,
result_table_columns)[evolve_metric]
log.info("Population scores: {}".format(population_scores))
log.info("Iteration #{} was done".format(iters))
iters += 1
def main():
args = parser.parse_args()
pipeline_config_path = find_config(args.config_path)
key_main_model = args.key_main_model
population_size = args.p_size
gpus = [int(gpu) for gpu in args.gpus.split(",")]
train_partition = int(args.train_partition)
start_from_population = int(args.start_from_population)
path_to_population = args.path_to_population
elitism_with_weights = args.elitism_with_weights
iterations = int(args.iterations)
p_crossover = args.p_cross
pow_crossover = args.pow_cross
p_mutation = args.p_mut
pow_mutation = args.pow_mut
if os.environ.get("CUDA_VISIBLE_DEVICES") is None:
pass
else:
cvd = [int(gpu) for gpu in os.environ.get("CUDA_VISIBLE_DEVICES").split(",")]
if gpus == [-1]:
gpus = cvd
else:
try:
gpus = [cvd[gpu] for gpu in gpus]
except IndexError:
raise ConfigError("Can not use gpus `{}` with CUDA_VISIBLE_DEVICES='{}'".format(
",".join(map(str, gpus)), ",".join(map(str, cvd))
))
basic_params = read_json(pipeline_config_path)
log.info("Given basic params: {}\n".format(json.dumps(basic_params, indent=2)))
# Initialize evolution
evolution = ParamsEvolution(population_size=population_size,
p_crossover=p_crossover, crossover_power=pow_crossover,
p_mutation=p_mutation, mutation_power=pow_mutation,
key_main_model=key_main_model,
seed=42,
train_partition=train_partition,
elitism_with_weights=elitism_with_weights,
**basic_params)
considered_metrics = evolution.get_value_from_config(evolution.basic_config,
list(evolution.find_model_path(
evolution.basic_config, "metrics"))[0] + ["metrics"])
considered_metrics = [metric['name'] if isinstance(metric, dict) else metric for metric in considered_metrics]
log.info(considered_metrics)
evolve_metric = considered_metrics[0]
# Create table variable for gathering results
abs_path_to_main_models = expand_path(str(evolution.models_path).format(
**evolution.basic_config['metadata']['variables']))
abs_path_to_main_models.mkdir(parents=True, exist_ok=True)
result_file = abs_path_to_main_models / "result_table.tsv"
print(result_file)
result_table_columns = []
result_table_dict = {}
for el in considered_metrics:
result_table_dict[el + "_valid"] = []
result_table_dict[el + "_test"] = []
result_table_columns.extend([el + "_valid", el + "_test"])
result_table_dict["params"] = []
result_table_columns.append("params")
if start_from_population == 0:
# if starting evolution from scratch
iters = 0
result_table = pd.DataFrame(result_table_dict)
# write down result table file
result_table.loc[:, result_table_columns].to_csv(result_file, index=False, sep='\t')
log.info("Iteration #{} starts".format(iters))
# randomly generate the first population
population = evolution.first_generation()
else:
# if starting evolution from already existing population
iters = start_from_population
log.info("Iteration #{} starts".format(iters))
population = []
for i in range(population_size):
config = read_json(expand_path(path_to_population) / f"model_{i}" / "config.json")
evolution.insert_value_or_dict_into_config(
config, evolution.path_to_models_save_path,
str(evolution.main_model_path / f"population_{start_from_population}" / f"model_{i}"))
population.append(config)
run_population(population, evolution, gpus)
population_scores = results_to_table(population, evolution, considered_metrics,
result_file, result_table_columns)[evolve_metric]
log.info("Population scores: {}".format(population_scores))
log.info("Iteration #{} was done".format(iters))
iters += 1
while True:
if iterations != -1 and start_from_population + iterations == iters:
log.info("End of evolution on iteration #{}".format(iters))
break
log.info("Iteration #{} starts".format(iters))
population = evolution.next_generation(population, population_scores, iters)
run_population(population, evolution, gpus)
population_scores = results_to_table(population, evolution, considered_metrics,
result_file, result_table_columns)[evolve_metric]
log.info("Population scores: {}".format(population_scores))
log.info("Iteration #{} was done".format(iters))
iters += 1