R-FCN+ResNet-50用自己的資料集訓練模型(python版本)
阿新 • • 發佈：2019-02-16
說明：
本文假設你已經做好資料集，格式和VOC2007一致，並且Linux系統已經配置好caffe所需環境（部落格裡教程很多），下面是訓練的一些修改。
py-R-FCN原始碼下載地址：
也有Matlab版本：
本文用到的是python版本。
準備工作：
（1）配置caffe環境(網上找教程)
（2）安裝cython, python-opencv, easydict
pip install cython
pip install easydict
apt-get install python-opencv然後，我們就可以開始配置R-FCN了。
1.下載py-R-FCN
git clone https://github.com/Orpine/py-R-FCN.git
下面稱你的py-R-FCN路徑為RFCN_ROOT.
2.下載caffe
注意，該caffe版本是微軟版本cd $RFCN_ROOT
git clone https://github.com/Microsoft/caffe.git3.Build Cython
cd $RFCN_ROOT/lib
make4.Build caffe和pycaffe
然後修改Makefile.config。caffe必須支援python層，所以WITH_PYTHON_LAYER := 1是必須的。其他配置可參考：Makefile.config 接著：cd $RFCN_ROOT/caffe cp Makefile.config.example Makefile.config
cd $RFCN_ROOT/caffe
make -j8 && make pycaffe
5.測試Demo
經過上面的工作，我們可以測試一下是否可以正常執行。 然後將模型放在$RFCN_ROOT/data。看起來是這樣的：$RFCN_ROOT/data/rfcn_models/resnet50_rfcn_final.caffemodel $RFCN_ROOT/data/rfcn_models/resnet101_rfcn_final.caffemodel
cd $RFCN_ROOT
./tools/demo_rfcn.py --net ResNet-50
6.用我們的資料集訓練
（1）拷貝資料集 假設我們已經做好資料集了，格式是和VOC2007一致，將你的資料集 拷貝到$RFCN_ROOT/data下。看起來是這樣的：$VOCdevkit0712/ # development kit $VOCdevkit/VOCcode/ # VOC utility code $VOCdevkit/VOC0712 # image sets, annotations, etc. # ... and several other directories ...如果你的資料夾名字不是VOCdevkit0712和VOC0712，修改成0712就行了。 （作者是用VOC2007和VOC2012訓練的，所以資料夾名字帶0712。也可以修改程式碼，但是那樣比較麻煩一些，修改資料夾比較簡單） （2）下載預訓練模型 本文以ResNet-50為例，因此下載ResNet-50-model.caffemodel。下載地址：連結：http://pan.baidu.com/s/1slRHD0L 密碼：r3ki 然後將caffemodel放在$RFCN_ROOT/data/imagenet_models (data下沒有該資料夾就新建一個)
（3）修改模型網路
開啟$RFCN_ROOT/models/pascal_voc/ResNet-50/rfcn_end2end (以end2end為例) 注意：下面的cls_num指的是你資料集的類別數+1（背景）。比如我有15類，+1類背景，cls_num=16. <1>修改class-aware/train_ohem.prototxtlayer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 16" #cls_num
}
}layer {
name: 'roi-data'
type: 'Python'
bottom: 'rpn_rois'
bottom: 'gt_boxes'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'rpn.proposal_target_layer'
layer: 'ProposalTargetLayer'
param_str: "'num_classes': 16" #cls_num
}
}layer {
bottom: "conv_new_1"
top: "rfcn_cls"
name: "rfcn_cls"
type: "Convolution"
convolution_param {
num_output: 784 #cls_num*(score_maps_size^2)
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "conv_new_1"
top: "rfcn_bbox"
name: "rfcn_bbox"
type: "Convolution"
convolution_param {
num_output: 3136 #4*cls_num*(score_maps_size^2)
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "rfcn_cls"
bottom: "rois"
top: "psroipooled_cls_rois"
name: "psroipooled_cls_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 16 #cls_num
group_size: 7
}
}layer {
bottom: "rfcn_bbox"
bottom: "rois"
top: "psroipooled_loc_rois"
name: "psroipooled_loc_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 64 #4*cls_num
group_size: 7
}
}<2>修改class-aware/test.prototxt
layer {
bottom: "conv_new_1"
top: "rfcn_cls"
name: "rfcn_cls"
type: "Convolution"
convolution_param {
num_output: 784 #cls_num*(score_maps_size^2)
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "conv_new_1"
top: "rfcn_bbox"
name: "rfcn_bbox"
type: "Convolution"
convolution_param {
num_output: 3136 #4*cls_num*(score_maps_size^2)
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "rfcn_cls"
bottom: "rois"
top: "psroipooled_cls_rois"
name: "psroipooled_cls_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 16 #cls_num
group_size: 7
}
}layer {
bottom: "rfcn_bbox"
bottom: "rois"
top: "psroipooled_loc_rois"
name: "psroipooled_loc_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 64 #4*cls_num
group_size: 7
}
}layer {
name: "cls_prob_reshape"
type: "Reshape"
bottom: "cls_prob_pre"
top: "cls_prob"
reshape_param {
shape {
dim: -1
dim: 16 #cls_num
}
}
}layer {
name: "bbox_pred_reshape"
type: "Reshape"
bottom: "bbox_pred_pre"
top: "bbox_pred"
reshape_param {
shape {
dim: -1
dim: 64 #4*cls_num
}
}
}<3>修改train_agnostic.prototxt
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 16" #cls_num
}
}layer {
bottom: "conv_new_1"
top: "rfcn_cls"
name: "rfcn_cls"
type: "Convolution"
convolution_param {
num_output: 784 #cls_num*(score_maps_size^2) ###
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "rfcn_cls"
bottom: "rois"
top: "psroipooled_cls_rois"
name: "psroipooled_cls_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 16 #cls_num ###
group_size: 7
}
}<4>修改train_agnostic_ohem.prototxt
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 16" #cls_num ###
}
}layer {
bottom: "conv_new_1"
top: "rfcn_cls"
name: "rfcn_cls"
type: "Convolution"
convolution_param {
num_output: 784 #cls_num*(score_maps_size^2) ###
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "rfcn_cls"
bottom: "rois"
top: "psroipooled_cls_rois"
name: "psroipooled_cls_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 16 #cls_num ###
group_size: 7
}
}layer {
bottom: "conv_new_1"
top: "rfcn_cls"
name: "rfcn_cls"
type: "Convolution"
convolution_param {
num_output: 784 #cls_num*(score_maps_size^2) ###
kernel_size: 1
pad: 0
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
}layer {
bottom: "rfcn_cls"
bottom: "rois"
top: "psroipooled_cls_rois"
name: "psroipooled_cls_rois"
type: "PSROIPooling"
psroi_pooling_param {
spatial_scale: 0.0625
output_dim: 16 #cls_num ###
group_size: 7
}
}layer {
name: "cls_prob_reshape"
type: "Reshape"
bottom: "cls_prob_pre"
top: "cls_prob"
reshape_param {
shape {
dim: -1
dim: 16 #cls_num ###
}
}
}(4)修改程式碼
<1>$RFCN/lib/datasets/pascal_voc.pyclass pascal_voc(imdb):
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'voc_' + year + '_' + image_set)
self._year = year
self._image_set = image_set
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'你的標籤1','你的標籤2',你的標籤3','你的標籤4'
)case $DATASET in
pascal_voc)
TRAIN_IMDB="voc_0712_trainval"
TEST_IMDB="voc_0712_test"
PT_DIR="pascal_voc"
ITERS=110000修改ITERS為你想要的迭代次數即可。
（5）開始訓練
cd $RFCN_ROOT
./experiments/scripts/rfcn_end2end_ohem.sh 0 ResNet-50 pascal_voc
$RFCN_ROOT/experiments/scripts裡還有一些其他的訓練方法，也可以測試一下（經過上面的修改，無ohem的end2end訓練也改好了，其他訓練方法修改的過程差不多）。
（6）結果
將訓練得到的模型($RFCN_ROOT/output/rfcn_end2end_ohem/voc_0712_trainval裡最後的caffemodel)拷貝到$RFCN_ROOT/data/rfcn_models下，然後開啟$RFCN_ROOT/tools/demo_rfcn.py，將CLASSES修改成你的標籤，NETS修改成你的model，im_names修改成你的測試圖片(放在data/demo下),最後：cd $RFCN_ROOT
./tools/demo_rfcn.py --net ResNet-50