Implement yaml.safe_load() (ultralytics#2876)

* Implement yaml.safe_load()

* yaml.safe_dump()

(cherry picked from commit f7bc685)

data/coco.yaml

@@ -30,6 +30,6 @@ names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', '
 
 # Print classes
 # with open('data/coco.yaml') as f:
-#   d = yaml.load(f, Loader=yaml.FullLoader)  # dict
+#   d = yaml.safe_load(f)  # dict
 #   for i, x in enumerate(d['names']):
 #     print(i, x)

models/yolo.py

@@ -72,7 +72,7 @@ def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, i
             import yaml  # for torch hub
             self.yaml_file = Path(cfg).name
             with open(cfg) as f:
-                self.yaml = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+                self.yaml = yaml.safe_load(f)  # model dict
 
         # Define model
         ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels

test.py

@@ -71,7 +71,7 @@ def test(data,
     if isinstance(data, str):
         is_coco = data.endswith('coco.yaml')
         with open(data) as f:
-            data = yaml.load(f, Loader=yaml.SafeLoader)
+            data = yaml.safe_load(f)
     check_dataset(data)  # check
     nc = 1 if single_cls else int(data['nc'])  # number of classes
     iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95

train.py

@@ -53,7 +53,7 @@
 def train(hyp, opt, device, tb_writer=None):
     logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
     save_dir, epochs, batch_size, total_batch_size, weights, rank = \
-        opt.save_dir, opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
+        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
 
     # Directories
     wdir = save_dir / 'weights'
@@ -64,16 +64,16 @@ def train(hyp, opt, device, tb_writer=None):
 
     # Save run settings
     with open(save_dir / 'hyp.yaml', 'w') as f:
-        yaml.dump(hyp, f, sort_keys=False)
+        yaml.safe_dump(hyp, f, sort_keys=False)
     with open(save_dir / 'opt.yaml', 'w') as f:
-        yaml.dump(vars(opt), f, sort_keys=False)
+        yaml.safe_dump(vars(opt), f, sort_keys=False)
 
     # Configure
     plots = not opt.evolve  # create plots
     cuda = device.type != 'cpu'
     init_seeds(2 + rank)
     with open(opt.data) as f:
-        data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+        data_dict = yaml.safe_load(f)  # data dict
     is_coco = opt.data.endswith('coco.yaml')
 
     # Logging- Doing this before checking the dataset. Might update data_dict
@@ -583,16 +583,17 @@ def train_ray_tune(config):
         assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
         apriori = opt.global_rank, opt.local_rank
         with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
-            opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader))  # replace
-        opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori  # reinstate
+            opt = argparse.Namespace(**yaml.safe_load(f))  # replace
+        opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = \
+            '', ckpt, True, opt.total_batch_size, *apriori  # reinstate
         logger.info('Resuming training from %s' % ckpt)
     else:
         # opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
         opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp)  # check files
         assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
         opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))  # extend to 2 sizes (train, test)
         opt.name = 'evolve' if opt.evolve else opt.name
-        opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve)  # increment run
+        opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve))
 
     # DDP mode
     opt.total_batch_size = opt.batch_size
@@ -607,7 +608,7 @@ def train_ray_tune(config):
 
     # Hyperparameters
     with open(opt.hyp) as f:
-        hyp = yaml.load(f, Loader=yaml.SafeLoader)  # load hyps
+        hyp = yaml.safe_load(f)  # load hyps
 
     # Train
     logger.info(opt)
@@ -686,7 +687,7 @@ def train_ray_tune(config):
         assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
         opt.notest, opt.nosave = True, True  # only test/save final epoch
         # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
-        yaml_file = opt.save_dir / 'hyp_evolved.yaml'  # save best result here
+        yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml'  # save best result here
         if opt.bucket:
             os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)  # download evolve.txt if exists
 

utils/autoanchor.py

@@ -102,7 +102,7 @@ def print_results(k):
 
     if isinstance(path, str):  # *.yaml file
         with open(path) as f:
-            data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+            data_dict = yaml.safe_load(f)  # model dict
         from utils.datasets import LoadImagesAndLabels
         dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
     else:

utils/aws/resume.py

@@ -19,7 +19,7 @@
 
     # Load opt.yaml
     with open(last.parent.parent / 'opt.yaml') as f:
-        opt = yaml.load(f, Loader=yaml.SafeLoader)
+        opt = yaml.safe_load(f)
 
     # Get device count
     d = opt['device'].split(',')  # devices

utils/general.py

@@ -553,7 +553,7 @@ def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
         results = tuple(x[0, :7])
         c = '%10.4g' * len(results) % results  # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
         f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
-        yaml.dump(hyp, f, sort_keys=False)
+        yaml.safe_dump(hyp, f, sort_keys=False)
 
     if bucket:
         os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket))  # upload

utils/plots.py

@@ -323,7 +323,7 @@ def plot_labels(labels, names=(), save_dir=Path(''), loggers=None):
 def plot_evolution(yaml_file='data/hyp.finetune.yaml'):  # from utils.plots import *; plot_evolution()
     # Plot hyperparameter evolution results in evolve.txt
     with open(yaml_file) as f:
-        hyp = yaml.load(f, Loader=yaml.SafeLoader)
+        hyp = yaml.safe_load(f)
     x = np.loadtxt('evolve.txt', ndmin=2)
     f = fitness(x)
     # weights = (f - f.min()) ** 2  # for weighted results

utils/wandb_logging/log_dataset.py

@@ -9,7 +9,7 @@
 
 def create_dataset_artifact(opt):
     with open(opt.data) as f:
-        data = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+        data = yaml.safe_load(f)  # data dict
     logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')
 
 

utils/wandb_logging/wandb_utils.py

@@ -55,7 +55,7 @@ def check_wandb_resume(opt):
 
 def process_wandb_config_ddp_mode(opt):
     with open(opt.data) as f:
-        data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+        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):
         api = wandb.Api()
@@ -73,7 +73,7 @@ def process_wandb_config_ddp_mode(opt):
     if train_dir or val_dir:
         ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml')
         with open(ddp_data_path, 'w') as f:
-            yaml.dump(data_dict, f)
+            yaml.safe_dump(data_dict, f)
         opt.data = ddp_data_path
 
 
@@ -121,7 +121,7 @@ def check_and_upload_dataset(self, opt):
                                                 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
         print("Created dataset config file ", config_path)
         with open(config_path) as f:
-            wandb_data_dict = yaml.load(f, Loader=yaml.SafeLoader)
+            wandb_data_dict = yaml.safe_load(f)
         return wandb_data_dict
 
     def setup_training(self, opt, data_dict):
@@ -193,7 +193,7 @@ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
 
     def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
         with open(data_file) as f:
-            data = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+            data = yaml.safe_load(f)  # data dict
         nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
         names = {k: v for k, v in enumerate(names)}  # to index dictionary
         self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
@@ -207,7 +207,7 @@ def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=
         path = data_file if overwrite_config else '_wandb.'.join(data_file.rsplit('.', 1))  # updated data.yaml path
         data.pop('download', None)
         with open(path, 'w') as f:
-            yaml.dump(data, f)
+            yaml.safe_dump(data, f)
 
         if self.job_type == 'Training':  # builds correct artifact pipeline graph
             self.wandb_run.use_artifact(self.val_artifact)