Add: retrainning bash command

retrain.sh

@@ -0,0 +1,38 @@
+export SERVER_NAME=virginia-ml
+export SERVER_NAME=ohio-ml
+export SERVER_NAME=oregon-ml
+export SERVER_NAME=canada-ml
+export SERVER_NAME=london-ml
+export SERVER_NAME=frankfurt-ml
+
+
+# 1. Check is it finished
+ssh ${SERVER_NAME}
+
+tmux attach -t train
+
+
+# 2. Check results
+ssh -L 6001:localhost:6006 ${SERVER_NAME}
+
+source activate tensorflow_p36
+tensorboard --logdir=logs
+
+cd /Users/aaron/Desktop/Code/dish-detection/models
+scp -r ${SERVER_NAME}:/home/ubuntu/logs/dish20181021T0457/events* .
+# scp -r ${SERVER_NAME}:/home/ubuntu/logs/dish20181021T0457/mask_rcnn_dish_0033.h5 .
+
+
+# 3. Prepare for restarting
+ssh ${SERVER_NAME}
+
+rm -rf logs
+vim dish.py
+
+## Change something if u want
+## vim dish.py
+tmux new -s train
+
+source activate tensorflow_p36
+pip install imgaug opencv-python
+python3 dish.py train --dataset=${PWD}/data --weights=coco --pairs BACKBONE=resnet101

setting.sh

@@ -1,5 +1,5 @@
 # 0. Initialize
-## Prepare two tabs, one for train, one for transfer data and tensorboard
+## Prepare two tabs, one for train, one for transfering data and tensorboard
 ## AMI: Ubuntu deeplearning ami 
 ## Storage: 100gib
 
@@ -53,7 +53,7 @@ source activate tensorflow_p36
 tensorboard --logdir=${PWD}/logs
 
 
-# 9. Run in tensorflow docker
+# Etc. Run in tensorflow docker
 cd ~/Desktop/gatten/Gatten_sushi_dishi_detection
 nvidia-docker run -d -p 8888:8888 -p 6006:6006 -e PASSWORD=1111 --name board -v ${PWD}:/notebooks/works tensorflow/tensorflow:latest-gpu-py3
 nvidia-docker exec -it board bash