You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
60 lines
1.2 KiB
60 lines
1.2 KiB
#!/bin/bash
|
|
|
|
if [ $# -lt 2 ] && [ $# -gt 3 ];then
|
|
echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
|
|
exit -1
|
|
fi
|
|
|
|
ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
|
echo "using $ngpu gpus..."
|
|
|
|
config_path=$1
|
|
ckpt_name=$2
|
|
ips=$3
|
|
|
|
if [ ! $ips ];then
|
|
ips_config=
|
|
else
|
|
ips_config="--ips="${ips}
|
|
fi
|
|
|
|
mkdir -p exp
|
|
|
|
# seed may break model convergence
|
|
seed=0
|
|
if [ ${seed} != 0 ]; then
|
|
export FLAGS_cudnn_deterministic=True
|
|
fi
|
|
|
|
# export FLAGS_cudnn_exhaustive_search=true
|
|
# export FLAGS_conv_workspace_size_limit=4000
|
|
|
|
# default memeory allocator strategy may case gpu training hang
|
|
# for no OOM raised when memory exhaused
|
|
export FLAGS_allocator_strategy=naive_best_fit
|
|
|
|
if [ ${ngpu} == 0 ]; then
|
|
python3 -u ${BIN_DIR}/train.py \
|
|
--ngpu ${ngpu} \
|
|
--config ${config_path} \
|
|
--output exp/${ckpt_name} \
|
|
--seed ${seed}
|
|
else
|
|
python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
|
|
--ngpu ${ngpu} \
|
|
--config ${config_path} \
|
|
--output exp/${ckpt_name} \
|
|
--seed ${seed}
|
|
fi
|
|
|
|
if [ ${seed} != 0 ]; then
|
|
unset FLAGS_cudnn_deterministic
|
|
fi
|
|
|
|
if [ $? -ne 0 ]; then
|
|
echo "Failed in training!"
|
|
exit 1
|
|
fi
|
|
|
|
exit 0
|