From e422c6197b5bcada0429986500d8d5ca4ffcb3e4 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 10 五月 2023 19:23:37 +0800
Subject: [PATCH] update repo
---
funasr/bin/train.py | 57 +++++++++++++++++++++++++++++++++------------------------
1 files changed, 33 insertions(+), 24 deletions(-)
diff --git a/funasr/bin/train.py b/funasr/bin/train.py
index 64391d9..22387b9 100755
--- a/funasr/bin/train.py
+++ b/funasr/bin/train.py
@@ -65,6 +65,7 @@
)
parser.add_argument(
"--dist_rank",
+ type=int,
default=None,
help="node rank for distributed training",
)
@@ -240,6 +241,12 @@
help="Enable resuming if checkpoint is existing",
)
parser.add_argument(
+ "--train_dtype",
+ default="float32",
+ choices=["float16", "float32", "float64"],
+ help="Data type for training.",
+ )
+ parser.add_argument(
"--use_amp",
type=str2bool,
default=False,
@@ -251,6 +258,12 @@
help="Show the logs every the number iterations in each epochs at the "
"training phase. If None is given, it is decided according the number "
"of training samples automatically .",
+ )
+ parser.add_argument(
+ "--use_tensorboard",
+ type=str2bool,
+ default=True,
+ help="Enable tensorboard logging",
)
# pretrained model related
@@ -296,39 +309,30 @@
help="whether to use dataloader for large dataset",
)
parser.add_argument(
- "--train_data_file",
+ "--dataset_conf",
+ action=NestedDictAction,
+ default=dict(),
+ help=f"The keyword arguments for dataset",
+ )
+ parser.add_argument(
+ "--data_dir",
type=str,
default=None,
- help="train_list for large dataset",
+ help="root path of data",
)
parser.add_argument(
- "--valid_data_file",
+ "--train_set",
type=str,
- default=None,
- help="valid_list for large dataset",
+ default="train",
+ help="train dataset",
)
parser.add_argument(
- "--train_data_path_and_name_and_type",
- 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",
- action="append",
- default=[],
- )
- parser.add_argument(
- "--train_shape_file",
- type=str, action="append",
- default=[],
- )
- parser.add_argument(
- "--valid_shape_file",
+ "--valid_set",
type=str,
- action="append",
- default=[],
+ default="validation",
+ help="dev dataset",
)
+
parser.add_argument(
"--use_preprocessor",
type=str2bool,
@@ -497,6 +501,10 @@
prepare_data(args, distributed_option)
model = build_model(args)
+ model = model.to(
+ dtype=getattr(torch, args.train_dtype),
+ device="cuda" if args.ngpu > 0 else "cpu",
+ )
optimizers = build_optimizer(args, model=model)
schedulers = build_scheduler(args, optimizers)
@@ -504,6 +512,7 @@
distributed_option.dist_rank,
distributed_option.local_rank))
logging.info(pytorch_cudnn_version())
+ logging.info("Args: {}".format(args))
logging.info(model_summary(model))
logging.info("Optimizer: {}".format(optimizers))
logging.info("Scheduler: {}".format(schedulers))
--
Gitblit v1.9.1