DeepLearningExamples/PyTorch/Detection/Efficientdet/distributed_train.sh

#!/bin/bash
# Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

NUM_PROC=$1
shift

mkdir ./EFFICIENTDET_DGX1_perf-train_AMP_NGPU8_BS-30

declare -a CMD
if [ -n "${SLURM_LOCALID-}" ]; then
  # Mode 1: Slurm launched a task for each GPU and set some envvars; no need for parallel launch
  if [ "${SLURM_NTASKS}" -gt "${SLURM_JOB_NUM_NODES}" ]; then
    CMD=( './bind.sh' '--cpu=exclusive' '--' 'python' '-u' )
  else
    CMD=( 'python' '-u' )
  fi
else
  # Mode 2: Single-node Docker; need to launch tasks with Pytorch's distributed launch
  CMD=( 'python' '-u' '-m' 'bind_launch' "--nproc_per_node=${NUM_PROC}" )
fi

"${CMD[@]}" train.py "$@"