add torch.backends.cudnn.benchmark=True in files

train.py

@@ -287,6 +287,7 @@ def train(hyp,  # path/to/hyp.yaml or hyp dictionary
         if RANK in [-1, 0]:
             pbar = tqdm(pbar, total=nb)  # progress bar
         optimizer.zero_grad()
+        torch.backends.cudnn.benchmark=True
         for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
             ni = i + nb * epoch  # number integrated batches (since train start)
             imgs = imgs.to(device, non_blocking=True).float() / 255.0  # uint8 to float32, 0-255 to 0.0-1.0