!6191 add imagenet for alexnet
Merge pull request !6191 from wukesong/imagenet-alexentpull/6191/MERGE
commit
f7c5c5265f
@ -0,0 +1,53 @@
|
||||
#!/bin/bash
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ============================================================================
|
||||
|
||||
if [ $# != 3 ]
|
||||
then
|
||||
echo "Usage: sh run_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [DATA_PATH]"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ ! -f $1 ]
|
||||
then
|
||||
echo "error: RANK_TABLE_FILE=$1 is not a file"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
ulimit -u unlimited
|
||||
export DEVICE_NUM=8
|
||||
export RANK_SIZE=8
|
||||
RANK_TABLE_FILE=$(realpath $1)
|
||||
export RANK_TABLE_FILE
|
||||
export DATASET_NAME=$2
|
||||
export DATA_PATH=$3
|
||||
echo "RANK_TABLE_FILE=${RANK_TABLE_FILE}"
|
||||
|
||||
export SERVER_ID=0
|
||||
rank_start=$((DEVICE_NUM * SERVER_ID))
|
||||
for((i=0; i<${DEVICE_NUM}; i++))
|
||||
do
|
||||
export DEVICE_ID=$i
|
||||
export RANK_ID=$((rank_start + i))
|
||||
rm -rf ./train_parallel$i
|
||||
mkdir ./train_parallel$i
|
||||
cp -r ./src ./train_parallel$i
|
||||
cp ./train.py ./train_parallel$i
|
||||
echo "start training for rank $RANK_ID, device $DEVICE_ID"
|
||||
cd ./train_parallel$i ||exit
|
||||
env > env.log
|
||||
python train.py --device_id=$i --dataset_name=$DATASET_NAME --data_path=$DATA_PATH > log 2>&1 &
|
||||
cd ..
|
||||
done
|
@ -0,0 +1,34 @@
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ============================================================================
|
||||
"""get parameters for Momentum optimizer"""
|
||||
def get_param_groups(network):
|
||||
"""get parameters"""
|
||||
decay_params = []
|
||||
no_decay_params = []
|
||||
for x in network.trainable_params():
|
||||
parameter_name = x.name
|
||||
if parameter_name.endswith('.bias'):
|
||||
# all bias not using weight decay
|
||||
no_decay_params.append(x)
|
||||
elif parameter_name.endswith('.gamma'):
|
||||
# bn weight bias not using weight decay, be carefully for now x not include BN
|
||||
no_decay_params.append(x)
|
||||
elif parameter_name.endswith('.beta'):
|
||||
# bn weight bias not using weight decay, be carefully for now x not include BN
|
||||
no_decay_params.append(x)
|
||||
else:
|
||||
decay_params.append(x)
|
||||
|
||||
return [{'params': no_decay_params, 'weight_decay': 0.0}, {'params': decay_params}]
|
Loading…
Reference in new issue