diff --git a/ultralytics/yolo/engine/trainer.py b/ultralytics/yolo/engine/trainer.py
index 4b0ac60..8f1f7b8 100644
--- a/ultralytics/yolo/engine/trainer.py
+++ b/ultralytics/yolo/engine/trainer.py
@@ -28,16 +28,19 @@ from ultralytics.yolo.utils import LOGGER, ROOT, TQDM_BAR_FORMAT
 from ultralytics.yolo.utils.checks import print_args
 from ultralytics.yolo.utils.files import increment_path, save_yaml
 from ultralytics.yolo.utils.modeling import get_model
-from ultralytics.yolo.utils.torch_utils import ModelEMA, de_parallel, one_cycle
+from ultralytics.yolo.utils.torch_utils import ModelEMA, de_parallel, init_seeds, one_cycle
 
 DEFAULT_CONFIG = ROOT / "yolo/utils/configs/default.yaml"
+RANK = int(os.getenv('RANK', -1))
 
 
 class BaseTrainer:
 
     def __init__(self, config=DEFAULT_CONFIG, overrides={}):
-        self.console = LOGGER
         self.args = self._get_config(config, overrides)
+        init_seeds(self.args.seed + 1 + RANK, deterministic=self.args.deterministic)
+
+        self.console = LOGGER
         self.validator = None
         self.model = None
         self.callbacks = defaultdict(list)
diff --git a/ultralytics/yolo/utils/configs/default.yaml b/ultralytics/yolo/utils/configs/default.yaml
index a57a6c2..fdb5d39 100644
--- a/ultralytics/yolo/utils/configs/default.yaml
+++ b/ultralytics/yolo/utils/configs/default.yaml
@@ -22,6 +22,7 @@ pretrained: False
 optimizer: 'SGD'  # choices=['SGD', 'Adam', 'AdamW', 'RMSProp']
 verbose: False
 seed: 0
+deterministic: True
 local_rank: -1
 single_cls: False  # train multi-class data as single-class
 image_weights: False  # use weighted image selection for training
diff --git a/ultralytics/yolo/utils/torch_utils.py b/ultralytics/yolo/utils/torch_utils.py
index b48160d..645b860 100644
--- a/ultralytics/yolo/utils/torch_utils.py
+++ b/ultralytics/yolo/utils/torch_utils.py
@@ -1,11 +1,13 @@
 import math
 import os
 import platform
+import random
 import time
 from contextlib import contextmanager
 from copy import deepcopy
 from pathlib import Path
 
+import numpy as np
 import thop
 import torch
 import torch.distributed as dist
@@ -199,6 +201,21 @@ def one_cycle(y1=0.0, y2=1.0, steps=100):
     return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
 
 
+def init_seeds(seed=0, deterministic=False):
+    # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)  # for Multi-GPU, exception safe
+    # torch.backends.cudnn.benchmark = True  # AutoBatch problem https://github.com/ultralytics/yolov5/issues/9287
+    if deterministic and check_version(torch.__version__, '1.12.0'):  # https://github.com/ultralytics/yolov5/pull/8213
+        torch.use_deterministic_algorithms(True)
+        torch.backends.cudnn.deterministic = True
+        os.environ['CUBLAS_WORKSPACE_CONFIG'] = ':4096:8'
+        os.environ['PYTHONHASHSEED'] = str(seed)
+
+
 class ModelEMA:
     """ Updated Exponential Moving Average (EMA) from https://github.com/rwightman/pytorch-image-models
     Keeps a moving average of everything in the model state_dict (parameters and buffers)