use the fluid.core.get_cuda_device_count to detect GPU numbers (#2939)

PaddleCV/image_classification/dist_train/dist_train.py

@@ -78,13 +78,7 @@ def parse_args():
 def get_device_num():
     if os.getenv("CPU_NUM"):
         return int(os.getenv("CPU_NUM"))
-    visible_device = os.getenv('CUDA_VISIBLE_DEVICES')
-    if visible_device:
-        device_num = len(visible_device.split(','))
-    else:
-        device_num = subprocess.check_output(
-            ['nvidia-smi', '-L']).decode().count('\n')
-    return device_num
+    return fluid.core.get_cuda_device_count()
 
 
 def prepare_reader(is_train, pyreader, args, pass_id=1):

PaddleCV/image_classification/fast_imagenet/train.py

@@ -62,18 +62,7 @@ def parse_args():
     return args
 
 
-def get_device_num():
-    import subprocess
-    visible_device = os.getenv('CUDA_VISIBLE_DEVICES')
-    if visible_device:
-        device_num = len(visible_device.split(','))
-    else:
-        device_num = subprocess.check_output(
-            ['nvidia-smi', '-L']).decode().count('\n')
-    return device_num
-
-
-DEVICE_NUM = get_device_num()
+DEVICE_NUM = fluid.core.get_cuda_device_count()
 
 
 def test_parallel(exe, test_args, args, test_reader, feeder, bs):

PaddleCV/rcnn/train.py

@@ -52,14 +52,9 @@ num_trainers = int(os.environ.get('PADDLE_TRAINERS_NUM', 1))
 
 def get_device_num():
     # NOTE(zcd): for multi-processe training, each process use one GPU card.
-    if num_trainers > 1: return 1
-    visible_device = os.environ.get('CUDA_VISIBLE_DEVICES', None)
-    if visible_device:
-        device_num = len(visible_device.split(','))
-    else:
-        device_num = subprocess.check_output(
-            ['nvidia-smi', '-L']).decode().count('\n')
-    return device_num
+    if num_trainers > 1:
+        return 1
+    return fluid.core.get_cuda_device_count()
 
 
 def train():

PaddleCV/yolov3/train.py

@@ -51,14 +51,9 @@ num_trainers = int(os.environ.get('PADDLE_TRAINERS_NUM', 1))
 
 def get_device_num():
     # NOTE(zcd): for multi-processe training, each process use one GPU card.
-    if num_trainers > 1: return 1
-    visible_device = os.environ.get('CUDA_VISIBLE_DEVICES', None)
-    if visible_device:
-        device_num = len(visible_device.split(','))
-    else:
-        device_num = subprocess.check_output(
-            ['nvidia-smi', '-L']).decode().count('\n')
-    return device_num
+    if num_trainers > 1:
+        return 1
+    return fluid.core.get_cuda_device_count()
 
 
 def train():

PaddleNLP/neural_machine_translation/transformer/train.py

@@ -158,14 +158,9 @@ def parse_args():
 
 def get_device_num():
     # NOTE(zcd): for multi-processe training, each process use one GPU card.
-    if num_trainers > 1: return 1
-    visible_device = os.environ.get('CUDA_VISIBLE_DEVICES', None)
-    if visible_device:
-        device_num = len(visible_device.split(','))
-    else:
-        device_num = subprocess.check_output(
-            ['nvidia-smi', '-L']).decode().count('\n')
-    return device_num
+    if num_trainers > 1:
+        return 1
+    return fluid.core.get_cuda_device_count()
 
 
 def append_nccl2_prepare(startup_prog, trainer_id, worker_endpoints,