!5407 fix yolov3-resnet18&ssd bool argument parse bug and modify README

Merge pull request !5407 from chengxb7532/master

model_zoo/official/cv/ssd/scripts/run_distribute_train.sh

@@ -31,7 +31,7 @@ fi
 # Before start distribute train, first create mindrecord files.
 BASE_PATH=$(cd "`dirname $0`" || exit; pwd)
 cd $BASE_PATH/../ || exit
-python train.py --only_create_dataset=1
+python train.py --only_create_dataset=True
 
 echo "After running the scipt, the network runs in the background. The log will be generated in LOGx/log.txt"
 
@@ -57,7 +57,7 @@ do
     if [ $# == 5 ]
     then
         python train.py  \
-        --distribute=1  \
+        --distribute=True  \
         --lr=$LR \
         --dataset=$DATASET \
         --device_num=$RANK_SIZE  \
@@ -68,7 +68,7 @@ do
     if [ $# == 7 ]
     then
         python train.py  \
-        --distribute=1  \
+        --distribute=True  \
         --lr=$LR \
         --dataset=$DATASET \
         --device_num=$RANK_SIZE  \

model_zoo/official/cv/ssd/train.py

@@ -17,6 +17,7 @@
 
 import os
 import argparse
+import ast
 import mindspore.nn as nn
 from mindspore import context, Tensor
 from mindspore.communication.management import init
@@ -33,9 +34,10 @@ from src.init_params import init_net_param, filter_checkpoint_parameter
 
 def main():
     parser = argparse.ArgumentParser(description="SSD training")
-    parser.add_argument("--only_create_dataset", type=bool, default=False, help="If set it true, only create "
-                                                                                "Mindrecord, default is False.")
-    parser.add_argument("--distribute", type=bool, default=False, help="Run distribute, default is False.")
+    parser.add_argument("--only_create_dataset", type=ast.literal_eval, default=False,
+                        help="If set it true, only create Mindrecord, default is False.")
+    parser.add_argument("--distribute", type=ast.literal_eval, default=False,
+                        help="Run distribute, default is False.")
     parser.add_argument("--device_id", type=int, default=0, help="Device id, default is 0.")
     parser.add_argument("--device_num", type=int, default=1, help="Use device nums, default is 1.")
     parser.add_argument("--lr", type=float, default=0.05, help="Learning rate, default is 0.05.")
@@ -47,7 +49,8 @@ def main():
     parser.add_argument("--pre_trained_epoch_size", type=int, default=0, help="Pretrained epoch size.")
     parser.add_argument("--save_checkpoint_epochs", type=int, default=10, help="Save checkpoint epochs, default is 10.")
     parser.add_argument("--loss_scale", type=int, default=1024, help="Loss scale, default is 1024.")
-    parser.add_argument("--filter_weight", type=bool, default=False, help="Filter weight parameters, default is False.")
+    parser.add_argument("--filter_weight", type=ast.literal_eval, default=False,
+                        help="Filter weight parameters, default is False.")
     args_opt = parser.parse_args()
 
     context.set_context(mode=context.GRAPH_MODE, device_target="Ascend", device_id=args_opt.device_id)

model_zoo/official/cv/yolov3_darknet53_quant/eval.py

@@ -210,20 +210,22 @@ def parse_args():
     parser = argparse.ArgumentParser('mindspore coco testing')
 
     # dataset related
-    parser.add_argument('--data_dir', type=str, default='', help='train data dir')
-    parser.add_argument('--per_batch_size', default=1, type=int, help='batch size for per gpu')
+    parser.add_argument('--data_dir', type=str, default="", help='Train data dir. Default: ""')
+    parser.add_argument('--per_batch_size', default=1, type=int, help='Batch size for per device, Default: 1')
 
     # network related
-    parser.add_argument('--pretrained', default='', type=str, help='model_path, local pretrained model to load')
+    parser.add_argument('--pretrained', default="", type=str,\
+                       help='The model path, local pretrained model to load, Default: ""')
 
     # logging related
-    parser.add_argument('--log_path', type=str, default='outputs/', help='checkpoint save location')
+    parser.add_argument('--log_path', type=str, default="outputs/", help='Log save location, Default: "outputs/"')
 
     # detect_related
-    parser.add_argument('--nms_thresh', type=float, default=0.5, help='threshold for NMS')
-    parser.add_argument('--annFile', type=str, default='', help='path to annotation')
-    parser.add_argument('--testing_shape', type=str, default='', help='shape for test ')
-    parser.add_argument('--ignore_threshold', type=float, default=0.001, help='threshold to throw low quality boxes')
+    parser.add_argument('--nms_thresh', type=float, default=0.5, help='Threshold for NMS. Default: 0.5')
+    parser.add_argument('--annFile', type=str, default="", help='The path to annotation. Default: ""')
+    parser.add_argument('--testing_shape', type=str, default="", help='Shape for test. Default: ""')
+    parser.add_argument('--ignore_threshold', type=float, default=0.001,\
+                       help='Threshold to throw low quality boxes, Default: 0.001')
 
     args, _ = parser.parse_known_args()
 

model_zoo/official/cv/yolov3_darknet53_quant/train.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ============================================================================
-"""YoloV3 train."""
+"""YoloV3-Darknet53-Quant train."""
 
 import os
 import time
@@ -32,7 +32,7 @@ from mindspore.train.quant import quant
 
 from src.yolo import YOLOV3DarkNet53, YoloWithLossCell, TrainingWrapper
 from src.logger import get_logger
-from src.util import AverageMeter, load_backbone, get_param_groups
+from src.util import AverageMeter, get_param_groups
 from src.lr_scheduler import warmup_step_lr, warmup_cosine_annealing_lr, \
     warmup_cosine_annealing_lr_V2, warmup_cosine_annealing_lr_sample
 from src.yolo_dataset import create_yolo_dataset
@@ -52,53 +52,60 @@ def parse_args():
     parser = argparse.ArgumentParser('mindspore coco training')
 
     # dataset related
-    parser.add_argument('--data_dir', type=str, default='', help='train data dir')
-    parser.add_argument('--per_batch_size', default=32, type=int, help='batch size for per gpu')
+    parser.add_argument('--data_dir', type=str, default='', help='Train data dir. Default: ""')
+    parser.add_argument('--per_batch_size', default=16, type=int, help='Batch size for per device. Default: 16')
 
     # network related
-    parser.add_argument('--pretrained_backbone', default='', type=str, help='model_path, local pretrained backbone'
-                                                                            ' model to load')
-    parser.add_argument('--resume_yolov3', default='', type=str, help='path of pretrained yolov3')
+    parser.add_argument('--resume_yolov3', default='', type=str,\
+                       help='The ckpt file of yolov3-darknet53, which used to yolov3-darknet53 quant. Default: ""')
 
     # optimizer and lr related
-    parser.add_argument('--lr_scheduler', default='exponential', type=str,
-                        help='lr-scheduler, option type: exponential, cosine_annealing')
-    parser.add_argument('--lr', default=0.001, type=float, help='learning rate of the training')
-    parser.add_argument('--lr_epochs', type=str, default='220,250', help='epoch of lr changing')
-    parser.add_argument('--lr_gamma', type=float, default=0.1,
-                        help='decrease lr by a factor of exponential lr_scheduler')
-    parser.add_argument('--eta_min', type=float, default=0., help='eta_min in cosine_annealing scheduler')
-    parser.add_argument('--T_max', type=int, default=320, help='T-max in cosine_annealing scheduler')
-    parser.add_argument('--max_epoch', type=int, default=320, help='max epoch num to train the model')
-    parser.add_argument('--warmup_epochs', default=0, type=float, help='warmup epoch')
-    parser.add_argument('--weight_decay', type=float, default=0.0005, help='weight decay')
-    parser.add_argument('--momentum', type=float, default=0.9, help='momentum')
+    parser.add_argument('--lr_scheduler', default='exponential', type=str,\
+                        help='Learning rate scheduler, option type: exponential, '
+                             'cosine_annealing. Default: exponential')
+    parser.add_argument('--lr', default=0.012, type=float, help='Learning rate of the training')
+    parser.add_argument('--lr_epochs', type=str, default='92,105',\
+                       help='Epoch of lr changing. Default: 92,105')
+    parser.add_argument('--lr_gamma', type=float, default=0.1,\
+                       help='Decrease lr by a factor of exponential lr_scheduler. Default: 0.1')
+    parser.add_argument('--eta_min', type=float, default=0.,\
+                       help='Eta_min in cosine_annealing scheduler. Default: 0.')
+    parser.add_argument('--T_max', type=int, default=135,\
+                       help='T-max in cosine_annealing scheduler. Default: 135')
+    parser.add_argument('--max_epoch', type=int, default=135,\
+                       help='Max epoch num to train the model. Default: 135')
+    parser.add_argument('--warmup_epochs', type=float, default=0, help='Warmup epochs. Default: 0')
+    parser.add_argument('--weight_decay', type=float, default=0.0005, help='Weight decay. Default: 0.0005')
+    parser.add_argument('--momentum', type=float, default=0.9, help='Momentum. Default: 0.9')
 
     # loss related
-    parser.add_argument('--loss_scale', type=int, default=1024, help='static loss scale')
-    parser.add_argument('--label_smooth', type=int, default=0, help='whether to use label smooth in CE')
-    parser.add_argument('--label_smooth_factor', type=float, default=0.1, help='smooth strength of original one-hot')
+    parser.add_argument('--loss_scale', type=int, default=1024, help='Static loss scale. Default: 1024')
+    parser.add_argument('--label_smooth', type=int, default=0, help='Whether to use label smooth in CE. Default: 0')
+    parser.add_argument('--label_smooth_factor', type=float, default=0.1,\
+                       help='Smooth strength of original one-hot. Default: 0.1')
 
     # logging related
-    parser.add_argument('--log_interval', type=int, default=100, help='logging interval')
-    parser.add_argument('--ckpt_path', type=str, default='outputs/', help='checkpoint save location')
-    parser.add_argument('--ckpt_interval', type=int, default=None, help='ckpt_interval')
-    parser.add_argument('--is_save_on_master', type=int, default=1, help='save ckpt on master or all rank')
+    parser.add_argument('--log_interval', type=int, default=100, help='Logging interval steps. Default: 100')
+    parser.add_argument('--ckpt_path', type=str, default='outputs/',\
+                       help='Checkpoint save location. Default: "outputs/"')
+    parser.add_argument('--ckpt_interval', type=int, default=None, help='Save checkpoint interval. Default: None')
+    parser.add_argument('--is_save_on_master', type=int, default=1,\
+                       help='Save ckpt on master or all rank, 1 for master, 0 for all ranks. Default: 1')
 
     # distributed related
-    parser.add_argument('--is_distributed', type=int, default=1, help='if multi device')
-    parser.add_argument('--rank', type=int, default=0, help='local rank of distributed')
-    parser.add_argument('--group_size', type=int, default=1, help='world size of distributed')
-
-    # roma obs
-    parser.add_argument('--train_url', type=str, default="", help='train url')
+    parser.add_argument('--is_distributed', type=int, default=0,\
+                       help='Distribute train or not, 1 for yes, 0 for no. Default: 0')
+    parser.add_argument('--rank', type=int, default=0, help='Local rank of distributed, Default: 0')
+    parser.add_argument('--group_size', type=int, default=1, help='World size of device, Default: 1')
 
     # profiler init
-    parser.add_argument('--need_profiler', type=int, default=0, help='whether use profiler')
+    parser.add_argument('--need_profiler', type=int, default=0,\
+                       help='Whether use profiler, 1 for yes, 0 for no, Default: 0')
 
     # reset default config
-    parser.add_argument('--training_shape', type=str, default="", help='fix training shape')
-    parser.add_argument('--resize_rate', type=int, default=None, help='resize rate for multi-scale training')
+    parser.add_argument('--training_shape', type=str, default="", help='Fix training shape. Default: ""')
+    parser.add_argument('--resize_rate', type=int, default=None,\
+                       help='Resize rate for multi-scale training. Default: None')
 
     args, _ = parser.parse_known_args()
     if args.lr_scheduler == 'cosine_annealing' and args.max_epoch > args.T_max:
@@ -141,7 +148,7 @@ def train():
     args.logger.save_args(args)
 
     if args.need_profiler:
-        from mindinsight.profiler.profiling import Profiler
+        from mindspore.profiler.profiling import Profiler
         profiler = Profiler(output_path=args.outputs_dir, is_detail=True, is_show_op_path=True)
 
     loss_meter = AverageMeter('loss')
@@ -159,12 +166,6 @@ def train():
     # default is kaiming-normal
     default_recurisive_init(network)
 
-    if args.pretrained_backbone:
-        network = load_backbone(network, args.pretrained_backbone, args)
-        args.logger.info('load pre-trained backbone {} into network'.format(args.pretrained_backbone))
-    else:
-        args.logger.info('Not load pre-trained backbone, please be careful')
-
     if args.resume_yolov3:
         param_dict = load_checkpoint(args.resume_yolov3)
         param_dict_new = {}

model_zoo/official/cv/yolov3_resnet18/README.md

@@ -118,9 +118,9 @@ After installing MindSpore via the official website, you can start training and
   ```
   Major parameters in train.py and config.py as follows:
 
-    evice_num: Use device nums, default is 1.
+    device_num: Use device nums, default is 1.
     lr: Learning rate, default is 0.001.
-    epoch_size: Epoch size, default is 10.
+    epoch_size: Epoch size, default is 50.
     batch_size: Batch size, default is 32.
     pre_trained: Pretrained Checkpoint file path.
     pre_trained_epoch_size: Pretrained epoch size.

model_zoo/official/cv/yolov3_resnet18/eval.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 # ============================================================================
 
-"""Evaluation for yolo_v3"""
+"""Evaluation for yolov3-resnet18"""
 import os
 import argparse
 import time

model_zoo/official/cv/yolov3_resnet18/scripts/run_distribute_train.sh

@@ -40,7 +40,7 @@ BASE_PATH=$(cd "`dirname $0`" || exit; pwd)
 cd $BASE_PATH/../ || exit
 
 # Before start distribute train, first create mindrecord files.
-python train.py --only_create_dataset=1 --mindrecord_dir=$MINDRECORD_DIR --image_dir=$IMAGE_DIR  \
+python train.py --only_create_dataset=True --mindrecord_dir=$MINDRECORD_DIR --image_dir=$IMAGE_DIR  \
 --anno_path=$ANNO_PATH
 if [ $? -ne 0 ]
 then
@@ -72,7 +72,7 @@ do
     if [ $# == 6 ]
     then
         taskset -c $cmdopt python train.py  \
-        --distribute=1  \
+        --distribute=True  \
         --lr=0.005 \
         --device_num=$RANK_SIZE  \
         --device_id=$DEVICE_ID  \
@@ -85,7 +85,7 @@ do
     if [ $# == 8 ]
     then
         taskset -c $cmdopt python train.py  \
-        --distribute=1  \
+        --distribute=True  \
         --lr=0.005 \
         --device_num=$RANK_SIZE  \
         --device_id=$DEVICE_ID  \

model_zoo/official/cv/yolov3_resnet18/train.py

@@ -24,6 +24,7 @@ Note if mindrecord_dir isn't empty, it will use mindrecord_dir rather than image
 
 import os
 import argparse
+import ast
 import numpy as np
 import mindspore.nn as nn
 from mindspore import context, Tensor
@@ -62,21 +63,21 @@ def init_net_param(network, init_value='ones'):
 
 def main():
     parser = argparse.ArgumentParser(description="YOLOv3 train")
-    parser.add_argument("--only_create_dataset", type=bool, default=False, help="If set it true, only create "
-                                                                                "Mindrecord, default is false.")
-    parser.add_argument("--distribute", type=bool, default=False, help="Run distribute, default is false.")
+    parser.add_argument("--only_create_dataset", type=ast.literal_eval, default=False,
+                        help="If set it true, only create Mindrecord, default is False.")
+    parser.add_argument("--distribute", type=ast.literal_eval, default=False, help="Run distribute, default is False.")
     parser.add_argument("--device_id", type=int, default=0, help="Device id, default is 0.")
     parser.add_argument("--device_num", type=int, default=1, help="Use device nums, default is 1.")
     parser.add_argument("--lr", type=float, default=0.001, help="Learning rate, default is 0.001.")
     parser.add_argument("--mode", type=str, default="sink", help="Run sink mode or not, default is sink")
-    parser.add_argument("--epoch_size", type=int, default=10, help="Epoch size, default is 10")
+    parser.add_argument("--epoch_size", type=int, default=50, help="Epoch size, default is 50")
     parser.add_argument("--batch_size", type=int, default=32, help="Batch size, default is 32.")
     parser.add_argument("--pre_trained", type=str, default=None, help="Pretrained checkpoint file path")
     parser.add_argument("--pre_trained_epoch_size", type=int, default=0, help="Pretrained epoch size")
     parser.add_argument("--save_checkpoint_epochs", type=int, default=5, help="Save checkpoint epochs, default is 5.")
     parser.add_argument("--loss_scale", type=int, default=1024, help="Loss scale, default is 1024.")
     parser.add_argument("--mindrecord_dir", type=str, default="./Mindrecord_train",
-                        help="Mindrecord directory. If the mindrecord_dir is empty, it wil generate mindrecord file by"
+                        help="Mindrecord directory. If the mindrecord_dir is empty, it wil generate mindrecord file by "
                              "image_dir and anno_path. Note if mindrecord_dir isn't empty, it will use mindrecord_dir "
                              "rather than image_dir and anno_path. Default is ./Mindrecord_train")
     parser.add_argument("--image_dir", type=str, default="", help="Dataset directory, "