From b9d1425028e480aa2c8dbd3502207e443dcd2060 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 25 四月 2023 01:09:03 +0800
Subject: [PATCH] update
---
funasr/bin/train.py | 51 +++++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 47 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/train.py b/funasr/bin/train.py
index 9c8f672..d3ebaac 100755
--- a/funasr/bin/train.py
+++ b/funasr/bin/train.py
@@ -21,7 +21,9 @@
from funasr.torch_utils.set_all_random_seed import set_all_random_seed
from funasr.utils.nested_dict_action import NestedDictAction
from funasr.utils.prepare_data import prepare_data
+from funasr.utils.types import int_or_none
from funasr.utils.types import str2bool
+from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils.yaml_no_alias_safe_dump import yaml_no_alias_safe_dump
@@ -58,18 +60,51 @@
)
parser.add_argument(
"--dist_world_size",
- default=None,
+ type=int,
+ default=1,
help="number of nodes for distributed training",
)
parser.add_argument(
"--dist_rank",
+ type=int,
default=None,
help="node rank for distributed training",
)
parser.add_argument(
"--local_rank",
+ type=int,
default=None,
help="local rank for distributed training",
+ )
+ parser.add_argument(
+ "--dist_master_addr",
+ default=None,
+ type=str_or_none,
+ help="The master address for distributed training. "
+ "This value is used when dist_init_method == 'env://'",
+ )
+ parser.add_argument(
+ "--dist_master_port",
+ default=None,
+ type=int_or_none,
+ help="The master port for distributed training"
+ "This value is used when dist_init_method == 'env://'",
+ )
+ parser.add_argument(
+ "--dist_launcher",
+ default=None,
+ type=str_or_none,
+ choices=["slurm", "mpi", None],
+ help="The launcher type for distributed training",
+ )
+ parser.add_argument(
+ "--multiprocessing_distributed",
+ default=True,
+ type=str2bool,
+ help="Use multi-processing distributed training to launch "
+ "N processes per node, which has N GPUs. This is the "
+ "fastest way to use PyTorch for either single node or "
+ "multi node data parallel training",
)
parser.add_argument(
"--unused_parameters",
@@ -263,6 +298,12 @@
help="whether to use dataloader for large dataset",
)
parser.add_argument(
+ "--dataset_conf",
+ action=NestedDictAction,
+ default=dict(),
+ help=f"The keyword arguments for dataset",
+ )
+ parser.add_argument(
"--train_data_file",
type=str,
default=None,
@@ -276,18 +317,21 @@
)
parser.add_argument(
"--train_data_path_and_name_and_type",
+ type=str2triple_str,
action="append",
default=[],
help="e.g. '--train_data_path_and_name_and_type some/path/a.scp,foo,sound'. ",
)
parser.add_argument(
"--valid_data_path_and_name_and_type",
+ type=str2triple_str,
action="append",
default=[],
)
parser.add_argument(
"--train_shape_file",
- type=str, action="append",
+ type=str,
+ action="append",
default=[],
)
parser.add_argument(
@@ -434,7 +478,6 @@
args, extra_task_params = parser.parse_known_args()
if extra_task_params:
args = build_args(args, parser, extra_task_params)
- # args = argparse.Namespace(**vars(args), **vars(task_args))
# set random seed
set_all_random_seed(args.seed)
@@ -444,7 +487,7 @@
# ddp init
os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpu_id)
- args.distributed = args.dist_world_size > 1
+ args.distributed = args.ngpu > 1 or args.dist_world_size > 1
distributed_option = build_distributed(args)
# for logging
--
Gitblit v1.9.1