未验证 提交 152ed916 编写于 作者: K kolinwei 提交者: GitHub

Merge pull request #2098 from jerrywgz/fix_rcnn_ce

fix config for ce
......@@ -7,11 +7,11 @@ export OMP_NUM_THREADS=1
cudaid=${face_detection:=0} # use 0-th card as default
export CUDA_VISIBLE_DEVICES=$cudaid
FLAGS_benchmark=true python train.py --model_save_dir=output/ --data_dir=dataset/coco/ --max_iter=100 --enable_ce --pretrained_model=./imagenet_resnet50_fusebn | python _ce.py
FLAGS_benchmark=true python train.py --model_save_dir=output/ --data_dir=dataset/coco/ --max_iter=500 --enable_ce --pretrained_model=./imagenet_resnet50_fusebn --learning_rate=0.00125 | python _ce.py
cudaid=${face_detection_m:=0,1,2,3} # use 0,1,2,3 card as default
export CUDA_VISIBLE_DEVICES=$cudaid
FLAGS_benchmark=true python train.py --model_save_dir=output/ --data_dir=dataset/coco/ --max_iter=100 --enable_ce --pretrained_model=./imagenet_resnet50_fusebn | python _ce.py
FLAGS_benchmark=true python train.py --model_save_dir=output/ --data_dir=dataset/coco/ --max_iter=500 --enable_ce --pretrained_model=./imagenet_resnet50_fusebn --learning_rate-0.005 | python _ce.py
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册