From 5fdfad576628d050eb38292d4d08ae9e39ab9c82 Mon Sep 17 00:00:00 2001 From: William Falcon Date: Fri, 4 Oct 2019 13:05:52 -0400 Subject: [PATCH] Update multi_node_cluster_auto_slurm.py --- .../multi_node_examples/multi_node_cluster_auto_slurm.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/examples/new_project_templates/multi_node_examples/multi_node_cluster_auto_slurm.py b/examples/new_project_templates/multi_node_examples/multi_node_cluster_auto_slurm.py index ce609b36..133e79a5 100644 --- a/examples/new_project_templates/multi_node_examples/multi_node_cluster_auto_slurm.py +++ b/examples/new_project_templates/multi_node_examples/multi_node_cluster_auto_slurm.py @@ -82,7 +82,8 @@ def main(hparams, cluster): checkpoint_callback=checkpoint, early_stop_callback=early_stop, gpus=hparams.per_experiment_nb_gpus, - nb_gpu_nodes=hyperparams.nb_gpu_nodes + nb_gpu_nodes=hyperparams.nb_gpu_nodes, + distributed_backend=hyperparams.distributed_backend ) # ------------------------ @@ -168,6 +169,8 @@ if __name__ == '__main__': help='where to save slurm meta') parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model') + parent_parser.add_argument('--distributed_backend', type=str, default='ddp', + help='ddp or ddp2') parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name') parent_parser.add_argument('--num_hyperparam_trials', type=int, default=6,