執行demo_rfcn.py只是跑人家訓練好的模型，接下來自己訓練。（VOC資料集）
1.準備資料
下載VOC資料集：

# Download the training, validation, test data and VOCdevkit
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.
 
tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar

2.解壓縮

# Extract all of these tars into one directory named VOCdevkit
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
tar xvf VOCtrainval_11-May-2012.tar

2、下載預訓練好的模型
下載的模型是指在ImageNet資料集上預訓練的ResNet模型，自己訓練VOC資料時是在這個預訓練的模型上進行fine-tuning的。
3.開始訓練

cd $RFCN_ROOT
./experiments/scripts/rfcn_end2end.sh 0 ResNet-50 pascal_voc

#  DATASET in {pascal_voc, coco} is the dataset to use(I only tested on pascal_voc)
# NET in {ResNet-50, ResNet-101}

output檔案：

# Trained R-FCN networks are saved under:
output/<experiment directory>/<dataset name>/

# Test outputs are saved under:
output/<experiment
 
 directory>/<dataset name>/<network snapshot name>/