diff --git a/tools/test.py b/tools/test.py
index a9d88b8074..e36eeeb3ea 100644
--- a/tools/test.py
+++ b/tools/test.py
@@ -49,6 +49,12 @@ def parse_args():
         '--gpu-collect',
         action='store_true',
         help='whether to use gpu to collect results.')
+    parser.add_argument(
+        '--gpu-id',
+        type=int,
+        default=0,
+        help='id of gpu to use '
+        '(only applicable to non-distributed testing)')
     parser.add_argument(
         '--tmpdir',
         help='tmp directory used for collecting results from multiple '
@@ -136,6 +142,8 @@ def main():
     cfg.model.pretrained = None
     cfg.data.test.test_mode = True
 
+    cfg.gpu_ids = [args.gpu_id]
+
     # init distributed env first, since logger depends on the dist info.
     if args.launcher == 'none':
         distributed = False
diff --git a/tools/train.py b/tools/train.py
index 81c7d854ea..258dd18e35 100644
--- a/tools/train.py
+++ b/tools/train.py
@@ -35,13 +35,19 @@ def parse_args():
     group_gpus.add_argument(
         '--gpus',
         type=int,
-        help='number of gpus to use '
+        help='(Deprecated, please use --gpu-id) number of gpus to use '
         '(only applicable to non-distributed training)')
     group_gpus.add_argument(
         '--gpu-ids',
         type=int,
         nargs='+',
-        help='ids of gpus to use '
+        help='(Deprecated, please use --gpu-id) ids of gpus to use '
+        '(only applicable to non-distributed training)')
+    group_gpus.add_argument(
+        '--gpu-id',
+        type=int,
+        default=0,
+        help='id of gpu to use '
         '(only applicable to non-distributed training)')
     parser.add_argument('--seed', type=int, default=None, help='random seed')
     parser.add_argument(
@@ -118,10 +124,20 @@ def main():
         cfg.load_from = args.load_from
     if args.resume_from is not None:
         cfg.resume_from = args.resume_from
+    if args.gpus is not None:
+        cfg.gpu_ids = range(1)
+        warnings.warn('`--gpus` is deprecated because we only support '
+                      'single GPU mode in non-distributed training. '
+                      'Use `gpus=1` now.')
     if args.gpu_ids is not None:
-        cfg.gpu_ids = args.gpu_ids
-    else:
-        cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
+        cfg.gpu_ids = args.gpu_ids[0:1]
+        warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
+                      'Because we only support single GPU mode in '
+                      'non-distributed training. Use the first GPU '
+                      'in `gpu_ids` now.')
+    if args.gpus is None and args.gpu_ids is None:
+        cfg.gpu_ids = [args.gpu_id]
+
     cfg.auto_resume = args.auto_resume
 
     # init distributed env first, since logger depends on the dist info.