Make reference scripts compatible with submitit (#3785)

* Add submitit script, partition param and parser on its own method.

* Fix method names, handle add_help correctly and refactoring.

* Delete run_with_submitit.py file

references/classification/train.py

@@ -224,9 +224,9 @@ def main(args):
     print('Training time {}'.format(total_time_str))
 
 
-def parse_args():
+def get_args_parser(add_help=True):
     import argparse
-    parser = argparse.ArgumentParser(description='PyTorch Classification Training')
+    parser = argparse.ArgumentParser(description='PyTorch Classification Training', add_help=add_help)
 
     parser.add_argument('--data-path', default='/datasets01/imagenet_full_size/061417/', help='dataset')
     parser.add_argument('--model', default='resnet18', help='model')
@@ -291,11 +291,9 @@ def parse_args():
                         help='number of distributed processes')
     parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')
 
-    args = parser.parse_args()
-
-    return args
+    return parser
 
 
 if __name__ == "__main__":
-    args = parse_args()
+    args = get_args_parser().parse_args()
     main(args)

references/classification/train_quantization.py

@@ -13,7 +13,6 @@ from train import train_one_epoch, evaluate, load_data
 
 
 def main(args):
-
     if args.output_dir:
         utils.mkdir(args.output_dir)
 
@@ -162,9 +161,9 @@ def main(args):
     print('Training time {}'.format(total_time_str))
 
 
-def parse_args():
+def get_args_parser(add_help=True):
     import argparse
-    parser = argparse.ArgumentParser(description='PyTorch Classification Training')
+    parser = argparse.ArgumentParser(description='PyTorch Quantized Classification Training', add_help=add_help)
 
     parser.add_argument('--data-path',
                         default='/datasets01/imagenet_full_size/061417/',
@@ -250,11 +249,9 @@ def parse_args():
                         default='env://',
                         help='url used to set up distributed training')
 
-    args = parser.parse_args()
-
-    return args
+    return parser
 
 
 if __name__ == "__main__":
-    args = parse_args()
+    args = get_args_parser().parse_args()
     main(args)

references/detection/train.py

@@ -51,7 +51,65 @@ def get_transform(train, data_augmentation):
     return presets.DetectionPresetTrain(data_augmentation) if train else presets.DetectionPresetEval()
 
 
+def get_args_parser(add_help=True):
+    import argparse
+    parser = argparse.ArgumentParser(description='PyTorch Detection Training', add_help=add_help)
+
+    parser.add_argument('--data-path', default='/datasets01/COCO/022719/', help='dataset')
+    parser.add_argument('--dataset', default='coco', help='dataset')
+    parser.add_argument('--model', default='maskrcnn_resnet50_fpn', help='model')
+    parser.add_argument('--device', default='cuda', help='device')
+    parser.add_argument('-b', '--batch-size', default=2, type=int,
+                        help='images per gpu, the total batch size is $NGPU x batch_size')
+    parser.add_argument('--epochs', default=26, type=int, metavar='N',
+                        help='number of total epochs to run')
+    parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
+                        help='number of data loading workers (default: 4)')
+    parser.add_argument('--lr', default=0.02, type=float,
+                        help='initial learning rate, 0.02 is the default value for training '
+                             'on 8 gpus and 2 images_per_gpu')
+    parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
+                        help='momentum')
+    parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
+                        metavar='W', help='weight decay (default: 1e-4)',
+                        dest='weight_decay')
+    parser.add_argument('--lr-step-size', default=8, type=int, help='decrease lr every step-size epochs')
+    parser.add_argument('--lr-steps', default=[16, 22], nargs='+', type=int, help='decrease lr every step-size epochs')
+    parser.add_argument('--lr-gamma', default=0.1, type=float, help='decrease lr by a factor of lr-gamma')
+    parser.add_argument('--print-freq', default=20, type=int, help='print frequency')
+    parser.add_argument('--output-dir', default='.', help='path where to save')
+    parser.add_argument('--resume', default='', help='resume from checkpoint')
+    parser.add_argument('--start_epoch', default=0, type=int, help='start epoch')
+    parser.add_argument('--aspect-ratio-group-factor', default=3, type=int)
+    parser.add_argument('--rpn-score-thresh', default=None, type=float, help='rpn score threshold for faster-rcnn')
+    parser.add_argument('--trainable-backbone-layers', default=None, type=int,
+                        help='number of trainable layers of backbone')
+    parser.add_argument('--data-augmentation', default="hflip", help='data augmentation policy (default: hflip)')
+    parser.add_argument(
+        "--test-only",
+        dest="test_only",
+        help="Only test the model",
+        action="store_true",
+    )
+    parser.add_argument(
+        "--pretrained",
+        dest="pretrained",
+        help="Use pre-trained models from the modelzoo",
+        action="store_true",
+    )
+
+    # distributed training parameters
+    parser.add_argument('--world-size', default=1, type=int,
+                        help='number of distributed processes')
+    parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')
+
+    return parser
+
+
 def main(args):
+    if args.output_dir:
+        utils.mkdir(args.output_dir)
+
     utils.init_distributed_mode(args)
     print(args)
 
@@ -147,61 +205,5 @@ def main(args):
 
 
 if __name__ == "__main__":
-    import argparse
-    parser = argparse.ArgumentParser(
-        description=__doc__)
-
-    parser.add_argument('--data-path', default='/datasets01/COCO/022719/', help='dataset')
-    parser.add_argument('--dataset', default='coco', help='dataset')
-    parser.add_argument('--model', default='maskrcnn_resnet50_fpn', help='model')
-    parser.add_argument('--device', default='cuda', help='device')
-    parser.add_argument('-b', '--batch-size', default=2, type=int,
-                        help='images per gpu, the total batch size is $NGPU x batch_size')
-    parser.add_argument('--epochs', default=26, type=int, metavar='N',
-                        help='number of total epochs to run')
-    parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
-                        help='number of data loading workers (default: 4)')
-    parser.add_argument('--lr', default=0.02, type=float,
-                        help='initial learning rate, 0.02 is the default value for training '
-                        'on 8 gpus and 2 images_per_gpu')
-    parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
-                        help='momentum')
-    parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
-                        metavar='W', help='weight decay (default: 1e-4)',
-                        dest='weight_decay')
-    parser.add_argument('--lr-step-size', default=8, type=int, help='decrease lr every step-size epochs')
-    parser.add_argument('--lr-steps', default=[16, 22], nargs='+', type=int, help='decrease lr every step-size epochs')
-    parser.add_argument('--lr-gamma', default=0.1, type=float, help='decrease lr by a factor of lr-gamma')
-    parser.add_argument('--print-freq', default=20, type=int, help='print frequency')
-    parser.add_argument('--output-dir', default='.', help='path where to save')
-    parser.add_argument('--resume', default='', help='resume from checkpoint')
-    parser.add_argument('--start_epoch', default=0, type=int, help='start epoch')
-    parser.add_argument('--aspect-ratio-group-factor', default=3, type=int)
-    parser.add_argument('--rpn-score-thresh', default=None, type=float, help='rpn score threshold for faster-rcnn')
-    parser.add_argument('--trainable-backbone-layers', default=None, type=int,
-                        help='number of trainable layers of backbone')
-    parser.add_argument('--data-augmentation', default="hflip", help='data augmentation policy (default: hflip)')
-    parser.add_argument(
-        "--test-only",
-        dest="test_only",
-        help="Only test the model",
-        action="store_true",
-    )
-    parser.add_argument(
-        "--pretrained",
-        dest="pretrained",
-        help="Use pre-trained models from the modelzoo",
-        action="store_true",
-    )
-
-    # distributed training parameters
-    parser.add_argument('--world-size', default=1, type=int,
-                        help='number of distributed processes')
-    parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')
-
-    args = parser.parse_args()
-
-    if args.output_dir:
-        utils.mkdir(args.output_dir)
-
+    args = get_args_parser().parse_args()
     main(args)

references/segmentation/train.py

@@ -172,9 +172,9 @@ def main(args):
     print('Training time {}'.format(total_time_str))
 
 
-def parse_args():
+def get_args_parser(add_help=True):
     import argparse
-    parser = argparse.ArgumentParser(description='PyTorch Segmentation Training')
+    parser = argparse.ArgumentParser(description='PyTorch Segmentation Training', add_help=add_help)
 
     parser.add_argument('--data-path', default='/datasets01/COCO/022719/', help='dataset path')
     parser.add_argument('--dataset', default='coco', help='dataset name')
@@ -215,10 +215,9 @@ def parse_args():
                         help='number of distributed processes')
     parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')
 
-    args = parser.parse_args()
-    return args
+    return parser
 
 
 if __name__ == "__main__":
-    args = parse_args()
+    args = get_args_parser().parse_args()
     main(args)