[Fix] Fix bug in non-distributed multi-gpu training/testing (#189)

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

* [Fix] add MMDP device_ids

tools/test.py

@@ -31,6 +31,12 @@ def parse_args():
         choices=['none', 'pytorch', 'slurm', 'mpi'],
         default='none',
         help='job launcher')
+    parser.add_argument(
+        '--gpu-id',
+        type=int,
+        default=0,
+        help='id of gpu to use '
+        '(only applicable to non-distributed testing)')
     parser.add_argument('--local_rank', type=int, default=0)
     parser.add_argument(
         '--cfg-options',
@@ -71,6 +77,7 @@ def main():
         work_type = args.config.split('/')[1]
         cfg.work_dir = osp.join('./work_dirs', work_type,
                                 osp.splitext(osp.basename(args.config))[0])
+    cfg.gpu_ids = [args.gpu_id]
 
     # init distributed env first, since logger depends on the dist info.
     if args.launcher == 'none':
@@ -98,7 +105,7 @@ def main():
     load_checkpoint(model, args.checkpoint, map_location='cpu')
 
     if not distributed:
-        model = MMDataParallel(model, device_ids=[0])
+        model = MMDataParallel(model, device_ids=cfg.gpu_ids)
         outputs = single_gpu_test(model, data_loader)
     else:
         model = MMDistributedDataParallel(

tools/train.py

@@ -4,6 +4,7 @@ import argparse
 import os
 import os.path as osp
 import time
+import warnings
 
 import mmcv
 import torch
@@ -28,13 +29,19 @@ def parse_args():
         '--gpus',
         type=int,
         default=1,
-        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(
@@ -88,10 +95,19 @@ 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]
 
     # init distributed env first, since logger depends on the dist info.
     if args.launcher == 'none':