diff --git a/train_asteroid.py b/train_asteroid.py
index eb56460..ed95e1a 100644
--- a/train_asteroid.py
+++ b/train_asteroid.py
@@ -42,7 +42,7 @@ parser.add_argument('--sample_rate', default=8000, type=int,
                     help='Sample rate')
 parser.add_argument('--segment', default=4, type=float,  # 取音频的长度，2s。#数据集语音长度要相同
                     help='Segment length (seconds)')
-parser.add_argument('--batch_size', default=2, type=int,  # 需要抛弃的音频长度
+parser.add_argument('--batch_size', default=3, type=int,  # 需要抛弃的音频长度
                     help='Batch size')
 
 # Network architecture
@@ -62,7 +62,7 @@ parser.add_argument('--norm', default='gln', type=str,
                     help='gln = "Global Norm", cln = "Cumulative Norm", ln = "Layer Norm"')
 parser.add_argument('--dropout', default=0.0, type=float,
                     help='dropout')
-parser.add_argument('--num_layers', default=5, type=int,
+parser.add_argument('--num_layers', default=4, type=int,
                     help='Number of Dual-Path-Block')
 parser.add_argument('--K', default=250, type=int,
                     help='The length of chunk')
@@ -110,8 +110,8 @@ def preprocess(args):
     print("preprocess done")
 
 def main(args):
-    context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target, save_graphs=True)
-    # context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target)
+    # context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target, save_graphs=True)
+    context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target)
 
     if args.run_distribute:
         print("distribute")