export CUDA_VISIBLE_DEVICES=0,1,2,3 python -m paddle.distributed.launch --log_dir ./mylog.time train.py --use_data_parallel 1 --batch_size=256 --reader_thread=8 --total_images=1281167 --class_dim=1000 --image_shape=3,224,224 --model_save_dir=output/ --lr_strategy=piecewise_decay --lr=0.1 --data_dir=../../PaddleCV/image_classification/data/ILSVRC2012 --l2_decay=3e-5 --model=MobileNetV1