diff --git a/train.py b/train.py
index 5ad47fe9ea6a..68cd7fab574c 100644
--- a/train.py
+++ b/train.py
@@ -198,6 +198,8 @@ def train(hyp,  # path/to/hyp.yaml or hyp dictionary
 
     # DP mode
     if cuda and RANK == -1 and torch.cuda.device_count() > 1:
+        logging.warning('DP not recommended, instead use torch.distributed.run for best DDP Multi-GPU results.\n'
+                        'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.')
         model = torch.nn.DataParallel(model)
 
     # SyncBatchNorm