Update script headers (#4163)

* Update download script headers

* cleanup

* bug fix attempt

* bug fix attempt2

* bug fix attempt3

* cleanup

utils/autoanchor.py

@@ -60,11 +60,11 @@ def check_anchors(dataset, model, thr=4.0, imgsz=640):
     print('')  # newline
 
 
-def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
     """ Creates kmeans-evolved anchors from training dataset
 
         Arguments:
-            path: path to dataset *.yaml, or a loaded dataset
+            dataset: path to data.yaml, or a loaded dataset
             n: number of anchors
             img_size: image size used for training
             thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
@@ -103,13 +103,11 @@ def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=10
             print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
         return k
 
-    if isinstance(path, str):  # *.yaml file
-        with open(path) as f:
+    if isinstance(dataset, str):  # *.yaml file
+        with open(dataset, encoding='ascii', errors='ignore') as f:
             data_dict = yaml.safe_load(f)  # model dict
         from utils.datasets import LoadImagesAndLabels
         dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
-    else:
-        dataset = path  # dataset
 
     # Get label wh
     shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)

utils/datasets.py

@@ -909,7 +909,7 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False):
             return False, None, path
 
     zipped, data_dir, yaml_path = unzip(Path(path))
-    with open(check_file(yaml_path)) as f:
+    with open(check_file(yaml_path), encoding='ascii', errors='ignore') as f:
         data = yaml.safe_load(f)  # data dict
         if zipped:
             data['path'] = data_dir  # TODO: should this be dir.resolve()?

utils/loggers/wandb/log_dataset.py

@@ -8,9 +8,9 @@ WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
 
 
 def create_dataset_artifact(opt):
-    with open(opt.data) as f:
+    with open(opt.data, encoding='ascii', errors='ignore') as f:
         data = yaml.safe_load(f)  # data dict
-    logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')
+    logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')  # TODO: return value unused
 
 
 if __name__ == '__main__':

utils/loggers/wandb/wandb_utils.py

@@ -62,7 +62,7 @@ def check_wandb_resume(opt):
 
 
 def process_wandb_config_ddp_mode(opt):
-    with open(check_file(opt.data)) as f:
+    with open(check_file(opt.data), encoding='ascii', errors='ignore') as f:
         data_dict = yaml.safe_load(f)  # data dict
     train_dir, val_dir = None, None
     if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX):
@@ -150,7 +150,7 @@ class WandbLogger():
                                                 opt.single_cls,
                                                 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
         print("Created dataset config file ", config_path)
-        with open(config_path) as f:
+        with open(config_path, encoding='ascii', errors='ignore') as f:
             wandb_data_dict = yaml.safe_load(f)
         return wandb_data_dict
 
@@ -226,7 +226,7 @@ class WandbLogger():
         print("Saving model artifact on epoch ", epoch + 1)
 
     def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
-        with open(data_file) as f:
+        with open(data_file, encoding='ascii', errors='ignore') as f:
             data = yaml.safe_load(f)  # data dict
         check_dataset(data)
         nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])