继续玩 Fast R-CNN

继续玩 Fast R-CNN

标签（空格分隔）：vision

---

Beyond the demo: installation for training and testing models

1. Download the training, validation, test data and VOCdevkit

   wget http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
   wget http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCtest_06-Nov-2007.tar
   wget http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

   没法下载，只能从其他地方下下来，然后传到Ubuntu机器上。

2. 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

3. It should have this basic structure

   $VOCdevkit/                           # development kit
   $VOCdevkit/VOCcode/                   # VOC utility code 
   $VOCdevkit/VOC2007                    # image sets,anotation
   
   # ... and several other directories ...
   

   VOCdevkit/VOCcode/ 这个目录我为什么没有？

4. Create symlinks for the PASCAL VOC dataset

   cd $FRCN_ROOT/data
   ln -s $VOCdevkit VOCdevkit2007

   Using symlinks is a good idea because you will likely want to share the same PASCAL dataset installation between multiple projects. 创建一个Symbolic (还是叫Soft) link是一个好的习惯。

5. [Optional] follow similar steps to get PASCAL VOC 2010 and 2012 (下载不了)

Download pre-computed Selective Search object proposals

Pre-computed selective search boxes can also be downloaded for VOC2007 and VOC2012.

cd $FRCN_ROOT
./data/scripts/fetch_selective_search_data.sh

This will populate the $FRCN_ROOT/data folder with selective_selective_data.
在这个目录中有如下一些Matlab的数据文件，很容易看出这些文件应该包含何种的内容，应该就是在各个图像上运行Selective Search得到的Roi Proposals。

voc_2007_test.mat   voc_2007_val.mat    voc_2012_trainval.mat
voc_2007_train.mat     voc_2012_test.mat   voc_2012_val.mat
voc_2007_trainval.mat  voc_2012_train.mat

Download pre-trained ImageNet models

Pre-trained ImageNet models can be downloaded for the three networks described in the paper: CaffeNet (model S), VGG_CNN_M_1024 (model M), and VGG16 (model L).
FR-CNN的输入有两个：一个是在ImageNet上训练的多层CNN的输出，另一个就是上面的Selective Search得到的Roi Proposals。所以这里把训练好的多层CNN下载下来(FR-CNN的Fine tune也不会修改这个层次的网络?)。

cd $FRCN_ROOT
./data/scripts/fetch_imagenet_models.sh

These models are all available in the Caffe Model Zoo, but are provided here for your convenience.

ls data/imagenet_models
CaffeNet.v2.caffemodel   (最小)
VGG16.v2.caffemodel    (最大)
VGG_CNN_M_1024.v2.caffemodel  (中等)

Usage

Train a Fast R-CNN detector. For example, train a VGG16 network on VOC 2007 trainval:

./tools/train_net.py --gpu 0 --solver models/VGG16/solver.prototxt \
    --weights data/imagenet_models/VGG16.v2.caffemodel

只是在CPU上试试，所以不能用上面的命令。改成：

./tools/train_net.py --cpu --solver models/CaffeNet/solver.prototxt --weights data/imagenet_models/CaffeNet.v2.caffemodel

If you see this error

EnvironmentError: MATLAB command 'matlab' not found. Please add 'matlab' to your PATH.

then you need to make sure the matlab binary is in your $PATH. MATLAB is currently required for PASCAL VOC evaluation.

Test a Fast R-CNN detector. For example, test the VGG 16 network on VOC 2007 test:

./tools/test_net.py --gpu 1 --def models/VGG16/test.prototxt \
    --net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000.caffemodel

Test output is written underneath $FRCN_ROOT/output.

Compress a Fast R-CNN model using truncated SVD on the fully-connected layers:

./tools/compress_net.py --def models/VGG16/test.prototxt \
    --def-svd models/VGG16/compressed/test.prototxt \
    --net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000.caffemodel
# Test the model you just compressed
./tools/test_net.py --gpu 0 --def models/VGG16/compressed/test.prototxt \
    --net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000_svd_fc6_1024_fc7_256.caffemodel

Experiment scripts

Scripts to reproduce the experiments in the paper (up to stochastic variation) are provided in $FRCN_ROOT/experiments/scripts. Log files for experiments are located in experiments/logs.

Note: Until recently (commit a566e39), the RNG seed for Caffe was not fixed during training. Now it’s fixed, unless train_net.py is called with the --rand flag.
Results generated before this commit will have some stochastic variation.

Extra downloads

• Experiment logs
• PASCAL VOC test set detections
  
  • voc_2007_test_results_fast_rcnn_caffenet_trained_on_2007_trainval.tgz
  • voc_2007_test_results_fast_rcnn_vgg16_trained_on_2007_trainval.tgz
  • voc_2007_test_results_fast_rcnn_vgg_cnn_m_1024_trained_on_2007_trainval.tgz
  • voc_2012_test_results_fast_rcnn_vgg16_trained_on_2007_trainvaltest_2012_trainval.tgz
  • voc_2012_test_results_fast_rcnn_vgg16_trained_on_2012_trainval.tgz
• Fast R-CNN VGG16 model trained on VOC07 train,val,test union with VOC12 train,val