assert torch!=1.12.0 for DDP training (#8621)

* assert torch!=1.12.0 for DDP training

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

utils/torch_utils.py

@@ -17,8 +17,13 @@ import torch
 import torch.distributed as dist
 import torch.nn as nn
 import torch.nn.functional as F
+from torch.nn.parallel import DistributedDataParallel as DDP
 
-from utils.general import LOGGER, colorstr, file_date, git_describe
+from utils.general import LOGGER, check_version, colorstr, file_date, git_describe
+
+LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
+RANK = int(os.getenv('RANK', -1))
+WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
 
 try:
     import thop  # for FLOPs computation
@@ -29,6 +34,17 @@ except ImportError:
 warnings.filterwarnings('ignore', message='User provided device_type of \'cuda\', but CUDA is not available. Disabling')
 
 
+def smart_DDP(model):
+    # Model DDP creation with checks
+    assert not check_version(torch.__version__, '1.12.0', pinned=True), \
+        'torch==1.12.0 torchvision==0.13.0 DDP training is not supported due to a known issue. ' \
+        'Please upgrade or downgrade torch to use DDP. See https://github.com/ultralytics/yolov5/issues/8395'
+    if check_version(torch.__version__, '1.11.0'):
+        return DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK, static_graph=True)
+    else:
+        return DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK)
+
+
 @contextmanager
 def torch_distributed_zero_first(local_rank: int):
     # Decorator to make all processes in distributed training wait for each local_master to do something