[Fix] Fix bug in non-distributed multi-gpu training/testing (#1197)

* Fix bug in non-distributed multi-gpu training/testing

* add deprecated warning to void BC-breaking

tools/test.py

@@ -28,6 +28,18 @@ def parse_args():
         action='store_true',
         help='Whether to fuse conv and bn, this will slightly increase'
         'the inference speed')
+    parser.add_argument(
+        '--gpu-ids',
+        type=int,
+        nargs='+',
+        help='(Deprecated, please use --gpu-id) ids of gpus to use '
+        '(only applicable to non-distributed training)')
+    parser.add_argument(
+        '--gpu-id',
+        type=int,
+        default=0,
+        help='id of gpu to use '
+        '(only applicable to non-distributed testing)')
     parser.add_argument(
         '--format-only',
         action='store_true',
@@ -140,6 +152,15 @@ def main():
             for ds_cfg in cfg.data.test:
                 ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
 
+    if args.gpu_ids is not None:
+        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 testing. Use the first GPU '
+                      'in `gpu_ids` now.')
+    else:
+        cfg.gpu_ids = [args.gpu_id]
+
     # init distributed env first, since logger depends on the dist info.
     if args.launcher == 'none':
         distributed = False
@@ -183,7 +204,7 @@ def main():
         model.PALETTE = dataset.PALETTE
 
     if not distributed:
-        model = MMDataParallel(model, device_ids=[0])
+        model = MMDataParallel(model, device_ids=cfg.gpu_ids)
         outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
     else:
         model = MMDistributedDataParallel(

tools/train.py

@@ -36,13 +36,19 @@ 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='number of gpus to use '
         '(only applicable to non-distributed training)')
     parser.add_argument('--seed', type=int, default=0, help='random seed')
     parser.add_argument(
@@ -112,10 +118,19 @@ def main():
                                 osp.splitext(osp.basename(args.config))[0])
     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]
 
     if args.autoscale_lr:
         # apply the linear scaling rule (https://arxiv.org/abs/1706.02677)