Set process daemon property and reset default value of num_proc_data arguments.

data_utils/utility.py

@@ -133,6 +133,7 @@ def xmap_readers_mp(mapper, reader, process_num, buffer_size, order=False):
         # start a read worker in a process
         target = order_read_worker if order else read_worker
         p = Process(target=target, args=(reader, in_queue))
+        p.daemon = True
         p.start()
 
         # start handle_workers with multiple processes
@@ -143,6 +144,7 @@ def xmap_readers_mp(mapper, reader, process_num, buffer_size, order=False):
             Process(target=target, args=args) for _ in xrange(process_num)
         ]
         for w in workers:
+            w.daemon = True
             w.start()
 
         # get results

examples/aishell/run_train.sh

@@ -9,7 +9,7 @@ python -u train.py \
 --batch_size=64 \
 --trainer_count=8 \
 --num_passes=50 \
---num_proc_data=12 \
+--num_proc_data=8 \
 --num_conv_layers=2 \
 --num_rnn_layers=3 \
 --rnn_layer_size=1024 \

examples/librispeech/run_train.sh

@@ -9,7 +9,7 @@ python -u train.py \
 --batch_size=512 \
 --trainer_count=8 \
 --num_passes=50 \
---num_proc_data=12 \
+--num_proc_data=8 \
 --num_conv_layers=2 \
 --num_rnn_layers=3 \
 --rnn_layer_size=2048 \

test.py

@@ -18,7 +18,7 @@ add_arg('batch_size',       int,    128,    "Minibatch size.")
 add_arg('trainer_count',    int,    8,      "# of Trainers (CPUs or GPUs).")
 add_arg('beam_size',        int,    500,    "Beam search width.")
 add_arg('num_proc_bsearch', int,    12,     "# of CPUs for beam search.")
-add_arg('num_proc_data',    int,    12,     "# of CPUs for data preprocessing.")
+add_arg('num_proc_data',    int,    4,      "# of CPUs for data preprocessing.")
 add_arg('num_conv_layers',  int,    2,      "# of convolution layers.")
 add_arg('num_rnn_layers',   int,    3,      "# of recurrent layers.")
 add_arg('rnn_layer_size',   int,    2048,   "# of recurrent cells per layer.")

train.py

@@ -16,7 +16,7 @@ add_arg = functools.partial(add_arguments, argparser=parser)
 add_arg('batch_size',       int,    256,    "Minibatch size.")
 add_arg('trainer_count',    int,    8,      "# of Trainers (CPUs or GPUs).")
 add_arg('num_passes',       int,    200,    "# of training epochs.")
-add_arg('num_proc_data',    int,    12,     "# of CPUs for data preprocessing.")
+add_arg('num_proc_data',    int,    8,      "# of CPUs for data preprocessing.")
 add_arg('num_conv_layers',  int,    2,      "# of convolution layers.")
 add_arg('num_rnn_layers',   int,    3,      "# of recurrent layers.")
 add_arg('rnn_layer_size',   int,    2048,   "# of recurrent cells per layer.")