From 2765c990f785df94f0b4b1c8058c68db90061999 Mon Sep 17 00:00:00 2001
From: puhuk <wetr235@gmail.com>
Date: Fri, 22 Oct 2021 21:22:02 +0900
Subject: [PATCH 1/5] Add type to default argument

To resolve issue #4694
---
 references/classification/train.py | 4 ++--
 references/detection/train.py      | 2 +-
 references/segmentation/train.py   | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/references/classification/train.py b/references/classification/train.py
index bae6adea63a..521f98ffcb0 100644
--- a/references/classification/train.py
+++ b/references/classification/train.py
@@ -386,8 +386,8 @@ def get_args_parser(add_help=True):
     parser.add_argument("--lr-step-size", default=30, 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=10, 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("--output-dir", default=".", type=str, help="path to save outputs")
+    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--cache-dataset",
diff --git a/references/detection/train.py b/references/detection/train.py
index e86762342cc..c884fcc61cb 100644
--- a/references/detection/train.py
+++ b/references/detection/train.py
@@ -77,7 +77,7 @@ def get_args_parser(add_help=True):
         help="weight decay (default: 1e-4)",
         dest="weight_decay",
     )
-    parser.add_argument("--lr-scheduler", default="multisteplr", help="the lr scheduler (default: multisteplr)")
+    parser.add_argument("--lr-scheduler", default="multisteplr", type=str, help="name of lr scheduler (default: multisteplr)")
     parser.add_argument(
         "--lr-step-size", default=8, type=int, help="decrease lr every step-size epochs (multisteplr scheduler only)"
     )
diff --git a/references/segmentation/train.py b/references/segmentation/train.py
index 73c49b6c543..8b264ac25dd 100644
--- a/references/segmentation/train.py
+++ b/references/segmentation/train.py
@@ -244,11 +244,11 @@ def get_args_parser(add_help=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")
+    parser.add_argument("--dist-url", default="env://", type=str, help="url used to set up distributed training")
 
     return parser
 
 
 if __name__ == "__main__":
     args = get_args_parser().parse_args()
-    main(args)
+    main(args)
\ No newline at end of file

From 345f528ae02dd4fad2fbb4a9699d8b1dc6795d98 Mon Sep 17 00:00:00 2001
From: puhuk <wetr235@gmail.com>
Date: Sat, 23 Oct 2021 00:27:27 +0900
Subject: [PATCH 2/5] Resolve issue #4694

Add missing types on argument parser
---
 references/classification/train.py | 12 ++++++------
 references/detection/train.py      | 16 ++++++++--------
 references/segmentation/train.py   | 14 +++++++-------
 3 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/references/classification/train.py b/references/classification/train.py
index 521f98ffcb0..46b3b257380 100644
--- a/references/classification/train.py
+++ b/references/classification/train.py
@@ -346,9 +346,9 @@ def get_args_parser(add_help=True):
 
     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")
-    parser.add_argument("--device", default="cuda", help="device")
+    parser.add_argument("--data-path", default="/datasets01/imagenet_full_size/061417/", type=str, help="dataset path")
+    parser.add_argument("--model", default="resnet18", type=str, help="model name")
+    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
     parser.add_argument("-b", "--batch-size", default=32, type=int)
     parser.add_argument("--epochs", default=90, type=int, metavar="N", help="number of total epochs to run")
     parser.add_argument(
@@ -377,7 +377,7 @@ def get_args_parser(add_help=True):
     )
     parser.add_argument("--mixup-alpha", default=0.0, type=float, help="mixup alpha (default: 0.0)")
     parser.add_argument("--cutmix-alpha", default=0.0, type=float, help="cutmix alpha (default: 0.0)")
-    parser.add_argument("--lr-scheduler", default="steplr", help="the lr scheduler (default: steplr)")
+    parser.add_argument("--lr-scheduler", default="steplr", type=str, help="the lr scheduler (default: steplr)")
     parser.add_argument("--lr-warmup-epochs", default=0, type=int, help="the number of epochs to warmup (default: 0)")
     parser.add_argument(
         "--lr-warmup-method", default="constant", type=str, help="the warmup method (default: constant)"
@@ -413,7 +413,7 @@ def get_args_parser(add_help=True):
         help="Use pre-trained models from the modelzoo",
         action="store_true",
     )
-    parser.add_argument("--auto-augment", default=None, help="auto augment policy (default: None)")
+    parser.add_argument("--auto-augment", default=None, type=str, help="auto augment policy (default: None)")
     parser.add_argument("--random-erase", default=0.0, type=float, help="random erasing probability (default: 0.0)")
 
     # Mixed precision training parameters
@@ -421,7 +421,7 @@ def get_args_parser(add_help=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")
+    parser.add_argument("--dist-url", default="env://", type=str, help="url used to set up distributed training")
     parser.add_argument(
         "--model-ema", action="store_true", help="enable tracking Exponential Moving Average of model parameters"
     )
diff --git a/references/detection/train.py b/references/detection/train.py
index c884fcc61cb..d47bae5032a 100644
--- a/references/detection/train.py
+++ b/references/detection/train.py
@@ -50,10 +50,10 @@ def get_args_parser(add_help=True):
 
     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("--data-path", default="/datasets01/COCO/022719/", type=str, help="dataset path")
+    parser.add_argument("--dataset", default="coco", type=str, help="dataset name")
+    parser.add_argument("--model", default="maskrcnn_resnet50_fpn", type=str, help="model name")
+    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
     parser.add_argument(
         "-b", "--batch-size", default=2, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
     )
@@ -92,15 +92,15 @@ def get_args_parser(add_help=True):
         "--lr-gamma", default=0.1, type=float, help="decrease lr by a factor of lr-gamma (multisteplr scheduler only)"
     )
     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("--output-dir", default=".", type=str, help="path where to save")
+    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
     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("--data-augmentation", default="hflip", type=str, help="data augmentation policy (default: hflip)")
     parser.add_argument(
         "--sync-bn",
         dest="sync_bn",
@@ -122,7 +122,7 @@ def get_args_parser(add_help=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")
+    parser.add_argument("--dist-url", default="env://", type=str, help="url used to set up distributed training")
 
     return parser
 
diff --git a/references/segmentation/train.py b/references/segmentation/train.py
index 8b264ac25dd..06709eb67ad 100644
--- a/references/segmentation/train.py
+++ b/references/segmentation/train.py
@@ -201,12 +201,12 @@ def get_args_parser(add_help=True):
 
     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")
-    parser.add_argument("--model", default="fcn_resnet101", help="model")
+    parser.add_argument("--data-path", default="/datasets01/COCO/022719/", type=str, help="dataset path")
+    parser.add_argument("--dataset", default="coco", type=str, help="dataset name")
+    parser.add_argument("--model", default="fcn_resnet101", type=str, help="model name")
     parser.add_argument("--aux-loss", action="store_true", help="auxiliar loss")
-    parser.add_argument("--device", default="cuda", help="device")
-    parser.add_argument("-b", "--batch-size", default=8, type=int)
+    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
+    parser.add_argument("-b", "--batch-size", default=8, type=int, help="size of batch")
     parser.add_argument("--epochs", default=30, type=int, metavar="N", help="number of total epochs to run")
 
     parser.add_argument(
@@ -227,8 +227,8 @@ def get_args_parser(add_help=True):
     parser.add_argument("--lr-warmup-method", default="linear", type=str, help="the warmup method (default: linear)")
     parser.add_argument("--lr-warmup-decay", default=0.01, type=float, help="the decay for lr")
     parser.add_argument("--print-freq", default=10, 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("--output-dir", default=".", type=str, help="path where to save")
+    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--test-only",

From 8f73e4fca4c93b2859420094c4c546ed11e7d578 Mon Sep 17 00:00:00 2001
From: puhuk <wetr235@gmail.com>
Date: Sat, 23 Oct 2021 01:32:08 +0900
Subject: [PATCH 3/5] Update with ufmt

formatted with ufmt
---
 references/detection/train.py    | 8 ++++++--
 references/segmentation/train.py | 2 +-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/references/detection/train.py b/references/detection/train.py
index d47bae5032a..ccab9532310 100644
--- a/references/detection/train.py
+++ b/references/detection/train.py
@@ -77,7 +77,9 @@ def get_args_parser(add_help=True):
         help="weight decay (default: 1e-4)",
         dest="weight_decay",
     )
-    parser.add_argument("--lr-scheduler", default="multisteplr", type=str, help="name of lr scheduler (default: multisteplr)")
+    parser.add_argument(
+        "--lr-scheduler", default="multisteplr", type=str, help="name of lr scheduler (default: multisteplr)"
+    )
     parser.add_argument(
         "--lr-step-size", default=8, type=int, help="decrease lr every step-size epochs (multisteplr scheduler only)"
     )
@@ -100,7 +102,9 @@ def get_args_parser(add_help=True):
     parser.add_argument(
         "--trainable-backbone-layers", default=None, type=int, help="number of trainable layers of backbone"
     )
-    parser.add_argument("--data-augmentation", default="hflip", type=str, help="data augmentation policy (default: hflip)")
+    parser.add_argument(
+        "--data-augmentation", default="hflip", type=str, help="data augmentation policy (default: hflip)"
+    )
     parser.add_argument(
         "--sync-bn",
         dest="sync_bn",
diff --git a/references/segmentation/train.py b/references/segmentation/train.py
index 06709eb67ad..7dec1e34027 100644
--- a/references/segmentation/train.py
+++ b/references/segmentation/train.py
@@ -251,4 +251,4 @@ def get_args_parser(add_help=True):
 
 if __name__ == "__main__":
     args = get_args_parser().parse_args()
-    main(args)
\ No newline at end of file
+    main(args)

From 0b50f308ae5a9fcd76de0e7bee53b45b85c089ce Mon Sep 17 00:00:00 2001
From: puhuk <wetr235@gmail.com>
Date: Sat, 23 Oct 2021 02:01:57 +0900
Subject: [PATCH 4/5] Updated with review

Updated with review
---
 references/classification/train.py |  8 +++++---
 references/detection/train.py      |  6 +++---
 references/segmentation/train.py   | 10 ++++++----
 3 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/references/classification/train.py b/references/classification/train.py
index 46b3b257380..16a68bbcb47 100644
--- a/references/classification/train.py
+++ b/references/classification/train.py
@@ -348,8 +348,10 @@ def get_args_parser(add_help=True):
 
     parser.add_argument("--data-path", default="/datasets01/imagenet_full_size/061417/", type=str, help="dataset path")
     parser.add_argument("--model", default="resnet18", type=str, help="model name")
-    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
-    parser.add_argument("-b", "--batch-size", default=32, type=int)
+    parser.add_argument("--device", default="cuda", type=str, help="device (Use cuda or cpu Default: cuda)")
+    parser.add_argument(
+        "-b", "--batch-size", default=32, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
+    )
     parser.add_argument("--epochs", default=90, type=int, metavar="N", help="number of total epochs to run")
     parser.add_argument(
         "-j", "--workers", default=16, type=int, metavar="N", help="number of data loading workers (default: 16)"
@@ -387,7 +389,7 @@ def get_args_parser(add_help=True):
     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=10, type=int, help="print frequency")
     parser.add_argument("--output-dir", default=".", type=str, help="path to save outputs")
-    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
+    parser.add_argument("--resume", default="", type=str, help="path of checkpoint")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--cache-dataset",
diff --git a/references/detection/train.py b/references/detection/train.py
index ccab9532310..4d1d9a30ab5 100644
--- a/references/detection/train.py
+++ b/references/detection/train.py
@@ -53,7 +53,7 @@ def get_args_parser(add_help=True):
     parser.add_argument("--data-path", default="/datasets01/COCO/022719/", type=str, help="dataset path")
     parser.add_argument("--dataset", default="coco", type=str, help="dataset name")
     parser.add_argument("--model", default="maskrcnn_resnet50_fpn", type=str, help="model name")
-    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
+    parser.add_argument("--device", default="cuda", type=str, help="device (Use cuda or cpu Default: cuda)")
     parser.add_argument(
         "-b", "--batch-size", default=2, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
     )
@@ -94,8 +94,8 @@ def get_args_parser(add_help=True):
         "--lr-gamma", default=0.1, type=float, help="decrease lr by a factor of lr-gamma (multisteplr scheduler only)"
     )
     parser.add_argument("--print-freq", default=20, type=int, help="print frequency")
-    parser.add_argument("--output-dir", default=".", type=str, help="path where to save")
-    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
+    parser.add_argument("--output-dir", default=".", type=str, help="path to save outputs")
+    parser.add_argument("--resume", default="", type=str, help="path of 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")
diff --git a/references/segmentation/train.py b/references/segmentation/train.py
index 7dec1e34027..4f44b5b5c1e 100644
--- a/references/segmentation/train.py
+++ b/references/segmentation/train.py
@@ -205,8 +205,10 @@ def get_args_parser(add_help=True):
     parser.add_argument("--dataset", default="coco", type=str, help="dataset name")
     parser.add_argument("--model", default="fcn_resnet101", type=str, help="model name")
     parser.add_argument("--aux-loss", action="store_true", help="auxiliar loss")
-    parser.add_argument("--device", default="cuda", type=str, help="device (cuda for GPU use, cpu for not using GPU")
-    parser.add_argument("-b", "--batch-size", default=8, type=int, help="size of batch")
+    parser.add_argument("--device", default="cuda", type=str, help="device (Use cuda or cpu Default: cuda)")
+    parser.add_argument(
+        "-b", "--batch-size", default=8, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
+    )
     parser.add_argument("--epochs", default=30, type=int, metavar="N", help="number of total epochs to run")
 
     parser.add_argument(
@@ -227,8 +229,8 @@ def get_args_parser(add_help=True):
     parser.add_argument("--lr-warmup-method", default="linear", type=str, help="the warmup method (default: linear)")
     parser.add_argument("--lr-warmup-decay", default=0.01, type=float, help="the decay for lr")
     parser.add_argument("--print-freq", default=10, type=int, help="print frequency")
-    parser.add_argument("--output-dir", default=".", type=str, help="path where to save")
-    parser.add_argument("--resume", default="", type=str, help="path for resume checkpoint from")
+    parser.add_argument("--output-dir", default=".", type=str, help="path to save outputs")
+    parser.add_argument("--resume", default="", type=str, help="path of checkpoint")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--test-only",

From cea89ebaa41f7b6f35be722b824b0ad70836e8a4 Mon Sep 17 00:00:00 2001
From: puhuk <wetr235@gmail.com>
Date: Sat, 23 Oct 2021 20:17:02 +0900
Subject: [PATCH 5/5] Update type of arguments

Add train.py from video_classification, similarity and train_quantization.py
---
 .../classification/train_quantization.py      | 18 +++++++++--------
 references/similarity/train.py                | 16 +++++++--------
 references/video_classification/train.py      | 20 ++++++++++---------
 3 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/references/classification/train_quantization.py b/references/classification/train_quantization.py
index f384be76a62..6e18557fe78 100644
--- a/references/classification/train_quantization.py
+++ b/references/classification/train_quantization.py
@@ -155,12 +155,14 @@ def get_args_parser(add_help=True):
 
     parser = argparse.ArgumentParser(description="PyTorch Quantized Classification Training", add_help=add_help)
 
-    parser.add_argument("--data-path", default="/datasets01/imagenet_full_size/061417/", help="dataset")
-    parser.add_argument("--model", default="mobilenet_v2", help="model")
-    parser.add_argument("--backend", default="qnnpack", help="fbgemm or qnnpack")
-    parser.add_argument("--device", default="cuda", help="device")
+    parser.add_argument("--data-path", default="/datasets01/imagenet_full_size/061417/", type=str, help="dataset path")
+    parser.add_argument("--model", default="mobilenet_v2", type=str, help="model name")
+    parser.add_argument("--backend", default="qnnpack", type=str, help="fbgemm or qnnpack")
+    parser.add_argument("--device", default="cuda", type=str, help="device (Use cuda or cpu Default: cuda)")
 
-    parser.add_argument("-b", "--batch-size", default=32, type=int, help="batch size for calibration/training")
+    parser.add_argument(
+        "-b", "--batch-size", default=32, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
+    )
     parser.add_argument("--eval-batch-size", default=128, type=int, help="batch size for evaluation")
     parser.add_argument("--epochs", default=90, type=int, metavar="N", help="number of total epochs to run")
     parser.add_argument(
@@ -203,8 +205,8 @@ def get_args_parser(add_help=True):
     parser.add_argument("--lr-step-size", default=30, 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=10, 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("--output-dir", default=".", type=str, help="path to save outputs")
+    parser.add_argument("--resume", default="", type=str, help="path of checkpoint")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--cache-dataset",
@@ -234,7 +236,7 @@ def get_args_parser(add_help=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")
+    parser.add_argument("--dist-url", default="env://", type=str, help="url used to set up distributed training")
 
     parser.add_argument(
         "--interpolation", default="bilinear", type=str, help="the interpolation method (default: bilinear)"
diff --git a/references/similarity/train.py b/references/similarity/train.py
index 4eab5e27188..f2793f551fe 100644
--- a/references/similarity/train.py
+++ b/references/similarity/train.py
@@ -137,19 +137,19 @@ def parse_args():
 
     parser = argparse.ArgumentParser(description="PyTorch Embedding Learning")
 
-    parser.add_argument("--dataset-dir", default="/tmp/fmnist/", help="FashionMNIST dataset directory path")
+    parser.add_argument("--dataset-dir", default="/tmp/fmnist/", type=str, help="FashionMNIST dataset directory path")
     parser.add_argument(
         "-p", "--labels-per-batch", default=8, type=int, help="Number of unique labels/classes per batch"
     )
     parser.add_argument("-k", "--samples-per-label", default=8, type=int, help="Number of samples per label in a batch")
-    parser.add_argument("--eval-batch-size", default=512, type=int)
-    parser.add_argument("--epochs", default=10, type=int, metavar="N", help="Number of training epochs to run")
-    parser.add_argument("-j", "--workers", default=4, type=int, metavar="N", help="Number of data loading workers")
-    parser.add_argument("--lr", default=0.0001, type=float, help="Learning rate")
+    parser.add_argument("--eval-batch-size", default=512, type=int, help="batch size for evaluation")
+    parser.add_argument("--epochs", default=10, 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")
+    parser.add_argument("--lr", default=0.0001, type=float, help="initial learning rate")
     parser.add_argument("--margin", default=0.2, type=float, help="Triplet loss margin")
-    parser.add_argument("--print-freq", default=20, type=int, help="Print frequency")
-    parser.add_argument("--save-dir", default=".", help="Model save directory")
-    parser.add_argument("--resume", default="", help="Resume from checkpoint")
+    parser.add_argument("--print-freq", default=20, type=int, help="print frequency")
+    parser.add_argument("--save-dir", default=".", type=str, help="Model save directory")
+    parser.add_argument("--resume", default="", type=str, help="path of checkpoint")
 
     return parser.parse_args()
 
diff --git a/references/video_classification/train.py b/references/video_classification/train.py
index 86c0daf738f..05077754f9a 100644
--- a/references/video_classification/train.py
+++ b/references/video_classification/train.py
@@ -288,16 +288,18 @@ def parse_args():
 
     parser = argparse.ArgumentParser(description="PyTorch Video Classification Training")
 
-    parser.add_argument("--data-path", default="/datasets01_101/kinetics/070618/", help="dataset")
-    parser.add_argument("--train-dir", default="train_avi-480p", help="name of train dir")
-    parser.add_argument("--val-dir", default="val_avi-480p", help="name of val dir")
-    parser.add_argument("--model", default="r2plus1d_18", help="model")
-    parser.add_argument("--device", default="cuda", help="device")
+    parser.add_argument("--data-path", default="/datasets01_101/kinetics/070618/", type=str, help="dataset path")
+    parser.add_argument("--train-dir", default="train_avi-480p", type=str, help="name of train dir")
+    parser.add_argument("--val-dir", default="val_avi-480p", type=str, help="name of val dir")
+    parser.add_argument("--model", default="r2plus1d_18", type=str, help="model name")
+    parser.add_argument("--device", default="cuda", type=str, help="device (Use cuda or cpu Default: cuda)")
     parser.add_argument("--clip-len", default=16, type=int, metavar="N", help="number of frames per clip")
     parser.add_argument(
         "--clips-per-video", default=5, type=int, metavar="N", help="maximum number of clips per video to consider"
     )
-    parser.add_argument("-b", "--batch-size", default=24, type=int)
+    parser.add_argument(
+        "-b", "--batch-size", default=24, type=int, help="images per gpu, the total batch size is $NGPU x batch_size"
+    )
     parser.add_argument("--epochs", default=45, type=int, metavar="N", help="number of total epochs to run")
     parser.add_argument(
         "-j", "--workers", default=10, type=int, metavar="N", help="number of data loading workers (default: 10)"
@@ -319,8 +321,8 @@ def parse_args():
     parser.add_argument("--lr-warmup-method", default="linear", type=str, help="the warmup method (default: linear)")
     parser.add_argument("--lr-warmup-decay", default=0.001, type=float, help="the decay for lr")
     parser.add_argument("--print-freq", default=10, 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("--output-dir", default=".", type=str, help="path to save outputs")
+    parser.add_argument("--resume", default="", type=str, help="path of checkpoint")
     parser.add_argument("--start-epoch", default=0, type=int, metavar="N", help="start epoch")
     parser.add_argument(
         "--cache-dataset",
@@ -360,7 +362,7 @@ def parse_args():
 
     # 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")
+    parser.add_argument("--dist-url", default="env://", type=str, help="url used to set up distributed training")
 
     args = parser.parse_args()