def main():
utils.display_args(args)
time.sleep(5)
# setting up reproducibility with selected seed
torch.manual_seed(args.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
# setting up the working directory and recording args
exp_tag = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
work_dir = os.path.join(args.work_dir, args.dataset, exp_tag)
os.makedirs("log", exist_ok=True)
log_path = os.path.join("log", exp_tag + ".log")
logger = get_logger(log_path)
res_list = []
config.DROPOUT = args.dropout
start = time.time()
for i in range(args.run):
logger.info("=" * 50 + f"Run {i+1}" + "=" * 50)
res = nas(logger)
res_list.append(res)
runnint_time = time.time() - start
result = pd.concat(res_list,
axis=0,
keys=[f"Run {i}" for i in range(len(res_list))])
if args.save is True:
os.makedirs(work_dir, exist_ok=False)
utils.save_args(args, os.path.join(work_dir, 'args.txt'))
file_name = os.path.join(work_dir, "result.csv")
result.to_csv(file_name, index=True)
logger.info(f"saving result to {file_name}")
fig_name = os.path.join(work_dir, "progress.png")
plt.figure()
avg_reward = result.groupby(
result.index.get_level_values(1))["reward"].mean()
plt.plot(avg_reward)
plt.title("Best reward in {} runs is {:.4f}".format(
args.run, result["reward"].max()))
logger.info(f"saving figure to {fig_name}")
plt.savefig(fig_name)
logger.info("Best reward in {} runs is {:.4f}".format(
args.run, result["reward"].max()))
device = 'cpu' if torch.cuda.is_available() is False else \
'cuda:{}'.format(args.gpu)
if args.evaluate is True:
test_result(args.dataset, res_list, device, logger, args.layers)
logger.info(f"Total running time {runnint_time}")
logger.info("*" * 50 + "End" + "*" * 50)
import numpy as np
from tqdm import tqdm
from utils import display_args, print_time
parser = argparse.ArgumentParser("Compute class weight in target labels.")
parser.add_argument("input_h5",
type=str,
help="Path to .h5 file containing target labels.")
parser.add_argument("output_npy",
type=str,
help="Path to output class occurrence .npy file.")
args = parser.parse_args()
display_args(args, __file__)
############## MAIN ##############
# Constant
OUTPUT_SIZE = 2
OUTPUT_KEY = "output_conserved"
start_time = time.time()
count = np.zeros(OUTPUT_SIZE)
with h5py.File(args.input_h5, "r") as label_dset:
label_group = label_dset[OUTPUT_KEY]
for group_name in tqdm(label_group.keys()):
target = label_group[group_name][:, :-3]
unique = np.unique(target, return_counts=True)
if len(unique[0]) != OUTPUT_SIZE:
raise RuntimeError(
model_desc = "{type}".format(
type=str(args.model_type))
with open("%sdnn_%s_pass_%05d.tar" %
(args.model_output_prefix, model_desc,
event.pass_id), "w") as f:
parameters.to_tar(f)
# training
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(reader.train(data_path,
feature_dim+1,
args.model_type.is_classification()),
buf_size=batch_size*10),
batch_size=batch_size),
feeding=feeding,
event_handler=event_handler,
num_passes=num_passes)
if __name__ == '__main__':
display_args(args)
train(
data_path=args.data_path,
model_type=ModelType(args.model_type),
batch_size=args.batch_size,
num_passes=args.num_passes,
class_num=args.class_num,
num_workers=args.num_workers,
use_gpu=args.use_gpu)
logger.info("save model: %sdssm_%s_pass_%05d.tar" %
(config.config['model_output_prefix'], model_desc, event.pass_id))
# if isinstance(event, paddle.event.EndPass):
# result = trainer.test(reader=test_reader, feeding=feeding)
# logger.info("Test with pass %d, %s" % (event.pass_id, result.metrics))
# with open("./data/output/endpass/dssm_params_pass" + str(event.pass_id) + ".tar", "w") as f:
# parameters.to_tar(f)
trainer.train(reader=train_reader,
event_handler=_event_handler,
feeding=feeding,
num_passes=num_passes)
logger.info("training finish.")
if __name__ == '__main__':
display_args(config.config)
train(train_data_paths=config.config["train_data_paths"],
test_data_paths=config.config["test_data_paths"],
source_dic_path=config.config["source_dic_path"],
target_dic_path=config.config["target_dic_path"],
model_arch=ModelArch(config.config["model_arch"]),
batch_size=config.config["batch_size"],
num_passes=config.config["num_passes"],
share_semantic_generator=config.config["share_network_between_source_target"],
share_embed=config.config["share_embed"],
class_num=config.config["class_num"],
num_workers=config.config["num_workers"],
use_gpu=config.config["use_gpu"])