From 0ad6301c9603130e020dfe52335dbb3e37210c19 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Mon, 26 Jul 2021 15:23:33 +0200
Subject: [PATCH] Update script headers (#4163)

* Update download script headers

* cleanup

* bug fix attempt

* bug fix attempt2

* bug fix attempt3

* cleanup
---
 data/scripts/download_weights.sh   |  9 +++++++--
 data/scripts/get_coco.sh           | 14 +++++++-------
 data/scripts/get_coco128.sh        | 16 ++++++++--------
 train.py                           |  5 +++--
 utils/autoanchor.py                | 10 ++++------
 utils/datasets.py                  |  2 +-
 utils/loggers/wandb/log_dataset.py |  4 ++--
 utils/loggers/wandb/wandb_utils.py |  6 +++---
 val.py                             |  2 +-
 9 files changed, 36 insertions(+), 32 deletions(-)

diff --git a/data/scripts/download_weights.sh b/data/scripts/download_weights.sh
index 6a279f163..5d74f0266 100755
--- a/data/scripts/download_weights.sh
+++ b/data/scripts/download_weights.sh
@@ -1,7 +1,12 @@
 #!/bin/bash
+# Copyright Ultralytics https://ultralytics.com, licensed under GNU GPL v3.0
 # Download latest models from https://github.com/ultralytics/yolov5/releases
-# Usage:
-#    $ bash path/to/download_weights.sh
+# YOLOv5 🚀 example usage: bash path/to/download_weights.sh
+# parent
+# └── yolov5
+#     ├── yolov5s.pt  ← downloads here
+#     ├── yolov5m.pt
+#     └── ...
 
 python - <<EOF
 from utils.google_utils import attempt_download
diff --git a/data/scripts/get_coco.sh b/data/scripts/get_coco.sh
index bce692c29..b3f838f53 100755
--- a/data/scripts/get_coco.sh
+++ b/data/scripts/get_coco.sh
@@ -1,11 +1,11 @@
 #!/bin/bash
-# COCO 2017 dataset http://cocodataset.org
-# Download command: bash data/scripts/get_coco.sh
-# Train command: python train.py --data coco.yaml
-# Default dataset location is next to YOLOv5:
-#   /parent_folder
-#     /coco
-#     /yolov5
+# Copyright Ultralytics https://ultralytics.com, licensed under GNU GPL v3.0
+# Download COCO 2017 dataset http://cocodataset.org
+# YOLOv5 🚀 example usage: bash data/scripts/get_coco.sh
+# parent
+# ├── yolov5
+# └── datasets
+#     └── coco  ← downloads here
 
 # Download/unzip labels
 d='../datasets' # unzip directory
diff --git a/data/scripts/get_coco128.sh b/data/scripts/get_coco128.sh
index 395043b5b..26bb8ad09 100644
--- a/data/scripts/get_coco128.sh
+++ b/data/scripts/get_coco128.sh
@@ -1,14 +1,14 @@
 #!/bin/bash
-# COCO128 dataset https://www.kaggle.com/ultralytics/coco128
-# Download command: bash data/scripts/get_coco128.sh
-# Train command: python train.py --data coco128.yaml
-# Default dataset location is next to /yolov5:
-#   /parent_folder
-#     /coco128
-#     /yolov5
+# Copyright Ultralytics https://ultralytics.com, licensed under GNU GPL v3.0
+# Download COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
+# YOLOv5 🚀 example usage: bash data/scripts/get_coco128.sh
+# parent
+# ├── yolov5
+# └── datasets
+#     └── coco128  ← downloads here
 
 # Download/unzip images and labels
-d='../' # unzip directory
+d='../datasets' # unzip directory
 url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
 f='coco128.zip' # or 'coco2017labels-segments.zip', 68 MB
 echo 'Downloading' $url$f ' ...'
diff --git a/train.py b/train.py
index db045c766..bd1fa9c74 100644
--- a/train.py
+++ b/train.py
@@ -78,8 +78,9 @@ def train(hyp,  # path/to/hyp.yaml or hyp dictionary
     plots = not evolve  # create plots
     cuda = device.type != 'cpu'
     init_seeds(1 + RANK)
-    with open(data) as f:
-        data_dict = yaml.safe_load(f)  # data dict
+    with open(data, encoding='ascii', errors='ignore') as f:
+        data_dict = yaml.safe_load(f)
+
     nc = 1 if single_cls else int(data_dict['nc'])  # number of classes
     names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
     assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}'  # check
diff --git a/utils/autoanchor.py b/utils/autoanchor.py
index 6abdd2d38..2571fc99a 100644
--- a/utils/autoanchor.py
+++ b/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)
diff --git a/utils/datasets.py b/utils/datasets.py
index d3edafa99..5b5ded4bb 100755
--- a/utils/datasets.py
+++ b/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()?
diff --git a/utils/loggers/wandb/log_dataset.py b/utils/loggers/wandb/log_dataset.py
index 3a9a3d79f..b5663c92e 100644
--- a/utils/loggers/wandb/log_dataset.py
+++ b/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__':
diff --git a/utils/loggers/wandb/wandb_utils.py b/utils/loggers/wandb/wandb_utils.py
index db2693a9e..581041acb 100644
--- a/utils/loggers/wandb/wandb_utils.py
+++ b/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'])
diff --git a/val.py b/val.py
index f20877e8a..c58bcdb20 100644
--- a/val.py
+++ b/val.py
@@ -123,7 +123,7 @@ def run(data,
         #     model = nn.DataParallel(model)
 
         # Data
-        with open(data) as f:
+        with open(data, encoding='ascii', errors='ignore') as f:
             data = yaml.safe_load(f)
         check_dataset(data)  # check