add training and testing scripts

Author: sshaoshuai

tools/scripts/dist_train.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+set -x
+NGPUS=$1
+PY_ARGS=${@:2}
+
+python -m torch.distributed.launch --nproc_per_node=${NGPUS} train.py --launcher pytorch ${PY_ARGS}
+

tools/scripts/slurm_test_single.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+set -x
+
+PARTITION=$1
+GPUS=1
+GPUS_PER_NODE=1
+PY_ARGS=${@:2}
+JOB_NAME=eval
+SRUN_ARGS=${SRUN_ARGS:-""}
+
+srun -p ${PARTITION} \
+    --job-name=${JOB_NAME} \
+    --gres=gpu:${GPUS_PER_NODE} \
+    --ntasks=${GPUS} \
+    --ntasks-per-node=${GPUS_PER_NODE} \
+    --kill-on-bad-exit=1 \
+    ${SRUN_ARGS} \
+    python -u test.py ${PY_ARGS}

tools/scripts/slurm_train.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+
+set -x
+
+PARTITION=$1
+JOB_NAME=$2
+GPUS=$3
+PY_ARGS=${@:4}
+
+GPUS_PER_NODE=${GPUS_PER_NODE:-8}
+CPUS_PER_TASK=${CPUS_PER_TASK:-5}
+SRUN_ARGS=${SRUN_ARGS:-""}
+
+
+srun -p ${PARTITION} \
+    --job-name=${JOB_NAME} \
+    --gres=gpu:${GPUS_PER_NODE} \
+    --ntasks=${GPUS} \
+    --ntasks-per-node=${GPUS_PER_NODE} \
+    --cpus-per-task=${CPUS_PER_TASK} \
+    --kill-on-bad-exit=1 \
+    ${SRUN_ARGS} \
+    python -u train.py --launcher slurm ${PY_ARGS}