def main():
parser = argparse.ArgumentParser()
parser.add_argument("-c",
"--config",
type=str,
required=True,
help="yaml file for config.")
parser.add_argument(
"-n",
"--name",
type=str,
default=None,
help="Name of the model. Used for both logging and saving chkpt.",
)
args = parser.parse_args()
hp = load_hparam(args.config)
if args.name is not None:
hp.log.name = args.name
# random seed
if hp.train.random_seed is None:
hp.train.random_seed = random.randint(1, 10000)
set_random_seed(hp.train.random_seed)
if hp.train.dist.gpus < 0:
hp.train.dist.gpus = torch.cuda.device_count()
if hp.model.device.lower() == "cpu" or hp.train.dist.gpus == 0:
train_loop(0, hp)
else:
distributed_run(train_loop, hp.to_dict(), hp.train.dist.gpus)
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-c",
"--config",
type=str,
required=True,
help="yaml file for config.")
parser.add_argument(
"-n",
"--name",
type=str,
default=None,
help="Name of the model. Used for both logging and saving chkpt.",
)
args = parser.parse_args()
hp = load_hparam(args.config)
if args.name is not None:
hp.log.name = args.name
# random seed
if hp.train.random_seed is None:
hp.train.random_seed = random.randint(1, 10000)
set_random_seed(hp.train.random_seed)
# set log/checkpoint dir
hp.log.chkpt_dir = os.path.join(hp.log.chkpt_dir, hp.log.name)
hp.log.log_dir = os.path.join(hp.log.log_dir, hp.log.name)
os.makedirs(hp.log.chkpt_dir, exist_ok=True)
os.makedirs(hp.log.log_dir, exist_ok=True)
# set logger
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
handlers=[
logging.FileHandler(
os.path.join(hp.log.log_dir,
"%s-%d.log" % (hp.log.name, time.time()))),
logging.StreamHandler(),
],
)
logger = logging.getLogger()
# set writer (tensorboard / wandb)
writer = Writer(hp, hp.log.log_dir)
hp_str = yaml.dump(hp.to_dict())
logger.info("Config:")
logger.info(hp_str)
if hp.data.train_dir == "" or hp.data.test_dir == "":
logger.error("train or test data directory cannot be empty.")
raise Exception("Please specify directories of data in %s" %
args.config)
train_loop(hp, logger, writer)
def test_net_arch():
hp = load_hparam("config/default.yaml")
net = Net_arch(hp)
# TODO: This is example code. You should change this part as you need. You can code this part as forward
x = torch.rand(64, 10)
x = net.fc1(x)
assert x.shape == (64, 10)
x = net.fc2(x)
assert x.shape == (64, 1)
def test_net_arch():
hp = load_hparam("config/default.yaml")
net = Net_arch(hp)
# TODO: This is example code. You should change this part as you need. You can code this part as forward
x = torch.rand(8, 1, 28, 28)
x = net.conv1(x) # x: (B,4,14,14)
assert x.shape == (8, 4, 14, 14)
x = net.conv2(x) # x: (B,4,7,7)
assert x.shape == (8, 4, 7, 7)
x = torch.flatten(x, 1) # x: (B,4*7*7)
assert x.shape == (8, 4 * 7 * 7)
x = net.fc(x) # x: (B,10)
assert x.shape == (8, 10)
def setup_method(self):
# set log/checkpoint dir
self.TEST_DIR = pathlib.Path(TEST_DIR)
self.log_dir = (self.TEST_DIR / "logs").resolve()
self.chkpt_dir = (self.TEST_DIR / "chkpt").resolve()
os.makedirs(self.TEST_DIR, exist_ok=True)
os.makedirs(self.log_dir, exist_ok=True)
os.makedirs(self.chkpt_dir, exist_ok=True)
# set hp
self.hp = load_hparam("config/default.yaml")
self.hp.model.device = "cpu"
self.hp.log.log_dir = self.log_dir
self.hp.log.chkpt_dir = self.chkpt_dir
self.hp.log.use_wandb = False
self.hp.log.use_tensorboard = False
# set logger
self.logger = make_logger(self.hp)