update scripts
This commit is contained in:
9
scripts-cluster/README.md
Normal file
9
scripts-cluster/README.md
Normal file
@@ -0,0 +1,9 @@
|
||||
# Commands on Cluster
|
||||
|
||||
## RNN
|
||||
```
|
||||
bash scripts-cluster/submit.sh yq01-v100-box-idl-2-8 WT2-GDAS 1 "bash ./scripts-rnn/train-WT2.sh GDAS"
|
||||
bash scripts-cluster/submit.sh yq01-v100-box-idl-2-8 PTB-GDAS 1 "bash ./scripts-rnn/train-PTB.sh GDAS"
|
||||
```
|
||||
|
||||
## CNN
|
@@ -1,6 +1,13 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
echo "CHECK-DATA-DIR START"
|
||||
sh /home/HGCP_Program/software-install/afs_mount/bin/afs_mount.sh \
|
||||
COMM_KM_Data COMM_km_2018 \
|
||||
`pwd`/hadoop-data \
|
||||
afs://xingtian.afs.baidu.com:9902/user/COMM_KM_Data/dongxuanyi/datasets
|
||||
|
||||
tar xvf ./hadoop-data/cifar.python.tar -C ./data/data/
|
||||
|
||||
cifar_dir="./data/data/cifar.python"
|
||||
if [ -d ${cifar_dir} ]; then
|
||||
echo "Find cifar-dir: "${cifar_dir}
|
||||
@@ -10,20 +17,17 @@ else
|
||||
fi
|
||||
echo "CHECK-DATA-DIR DONE"
|
||||
|
||||
sh /home/HGCP_Program/software-install/afs_mount/bin/afs_mount.sh \
|
||||
COMM_KM_Data COMM_km_2018 \
|
||||
`pwd`/hadoop-data \
|
||||
afs://xingtian.afs.baidu.com:9902/user/COMM_KM_Data/dongxuanyi/datasets
|
||||
|
||||
echo "PWD: " `pwd`
|
||||
echo "files:: " `ls`
|
||||
echo "CUDA_VISIBLE_DEVICES: " ${CUDA_VISIBLE_DEVICES}
|
||||
|
||||
# config python
|
||||
PYTHON_ENV=py36_pytorch1.0_env0.1.3.tar.gz
|
||||
wget -e "http_proxy=cp01-sys-hic-gpu-02.cp01:8888" http://cp01-sys-hic-gpu-02.cp01/HGCP_DEMO/$PYTHON_ENV > screen.log 2>&1
|
||||
tar xzf $PYTHON_ENV
|
||||
|
||||
alias python="./env/bin/python"
|
||||
echo "JOB-PWD : " `pwd`
|
||||
echo "JOB-files : " `ls`
|
||||
echo "JOB-CUDA_VISIBLE_DEVICES: " ${CUDA_VISIBLE_DEVICES}
|
||||
|
||||
echo "Python: " `which python`
|
||||
echo `./env/bin/python --version`
|
||||
|
||||
# real commands
|
||||
bash ./scripts-rnn/train-WT2.sh GDAS
|
||||
|
@@ -18,14 +18,15 @@ QUEUE=$1
|
||||
NAME=$2
|
||||
GPUs=$3
|
||||
CMD=$4
|
||||
TIME=$(date +"%Y-%h-%d-%T")
|
||||
TIME=$(date +"%Y-%h-%d--%T")
|
||||
TIME="${TIME//:/-}"
|
||||
|
||||
JOB_SCRIPT="${FDIR}/tmps/job-${TIME}.sh"
|
||||
echo "JOB-SCRIPT: " ${JOB_SCRIPT}
|
||||
|
||||
cat ${FDIR}/job-script.sh > ${JOB_SCRIPT}
|
||||
echo ${CMD} >> ${JOB_SCRIPT}
|
||||
|
||||
exit 1
|
||||
HGCP_CLIENT_BIN="${HOME}/.hgcp/software-install/HGCP_client/bin"
|
||||
|
||||
|
||||
@@ -42,3 +43,6 @@ ${HGCP_CLIENT_BIN}/submit \
|
||||
--gpu-pnode ${GPUs} \
|
||||
--time-limit 0 \
|
||||
--job-script ${JOB_SCRIPT}
|
||||
|
||||
#--job-script ${FDIR}/job-script.sh
|
||||
#echo "JOB-SCRIPT: " ${JOB_SCRIPT}
|
||||
|
Reference in New Issue
Block a user