Fixed dataloader CPU bottleneck for small batch sizes (#7659)

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

ultralytics/data/build.py

@@ -107,7 +107,7 @@ def build_dataloader(dataset, batch, workers, shuffle=True, rank=-1):
     """Return an InfiniteDataLoader or DataLoader for training or validation set."""
     batch = min(batch, len(dataset))
     nd = torch.cuda.device_count()  # number of CUDA devices
-    nw = min([os.cpu_count() // max(nd, 1), batch, workers])  # number of workers
+    nw = min([os.cpu_count() // max(nd, 1), workers])  # number of workers
     sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
     generator = torch.Generator()
     generator.manual_seed(6148914691236517205 + RANK)