diff --git a/train.py b/train.py
index 39b996c34a38..8c07ec2a744f 100644
--- a/train.py
+++ b/train.py
@@ -123,6 +123,10 @@ def train(hyp, opt, device, tb_writer=None):
             epochs += ckpt['epoch']  # finetune additional epochs
 
         del ckpt, state_dict
+    
+    # Image sizes
+    gs = int(max(model.stride))  # grid size (max stride)
+    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples
 
     # DP mode
     if cuda and rank == -1 and torch.cuda.device_count() > 1:
@@ -140,10 +144,6 @@ def train(hyp, opt, device, tb_writer=None):
     if cuda and rank != -1:
         model = DDP(model, device_ids=[opt.local_rank], output_device=(opt.local_rank))
 
-    # Image sizes
-    gs = int(max(model.stride))  # grid size (max stride)
-    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples
-
     # Trainloader
     dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt, hyp=hyp, augment=True,
                                             cache=opt.cache_images, rect=opt.rect, local_rank=rank,