From 803f4013a27465ec7d95845d22e23be893b38339 Mon Sep 17 00:00:00 2001 From: Thomas Friedel Date: Sun, 26 May 2024 02:14:09 +0200 Subject: [PATCH] re-added commented out debug print --- ultralytics/engine/trainer.py | 1 + 1 file changed, 1 insertion(+) diff --git a/ultralytics/engine/trainer.py b/ultralytics/engine/trainer.py index da34d65c..82a398c4 100644 --- a/ultralytics/engine/trainer.py +++ b/ultralytics/engine/trainer.py @@ -224,6 +224,7 @@ class BaseTrainer: """Initializes and sets the DistributedDataParallel parameters for training.""" torch.cuda.set_device(RANK) self.device = torch.device("cuda", RANK) + # LOGGER.info(f'DDP info: RANK {RANK}, WORLD_SIZE {world_size}, DEVICE {self.device}') os.environ["TORCH_NCCL_BLOCKING_WAIT"] = "1" # set to enforce timeout dist.init_process_group( backend="nccl" if dist.is_nccl_available() else "gloo",