first commit

Y5/utils/aws/resume.py

@@ -1,4 +1,4 @@
-# Resume all interrupted trainings in yolov5/ dir including DPP trainings
+# Resume all interrupted trainings in yolov5/ dir including DDP trainings
 # Usage: $ python utils/aws/resume.py
 
 import os
@@ -8,7 +8,10 @@ from pathlib import Path
 import torch
 import yaml
 
-sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[2]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
 
 port = 0  # --master_port
 path = Path('').resolve()
@@ -18,8 +21,8 @@ for last in path.rglob('*/**/last.pt'):
         continue
 
     # Load opt.yaml
-    with open(last.parent.parent / 'opt.yaml') as f:
-        opt = yaml.load(f, Loader=yaml.SafeLoader)
+    with open(last.parent.parent / 'opt.yaml', errors='ignore') as f:
+        opt = yaml.safe_load(f)
 
     # Get device count
     d = opt['device'].split(',')  # devices
@@ -28,7 +31,7 @@ for last in path.rglob('*/**/last.pt'):
 
     if ddp:  # multi-GPU
         port += 1
-        cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
+        cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
     else:  # single-GPU
         cmd = f'python train.py --resume {last}'