py faster rcnn训练 VGG_CNN_M_1024记录

ZF网络已经训练通过，参考训练ZF的步骤修改相关文件。环境：CPU+ Ubuntu16.04

1、修改py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt & stage2_fast_rcnn_train.pt

layer {
name: 'data'
type: 'Python'
top: 'data'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2"#original is 21 ,class_num + 1
}
}

layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param { lr_mult: 1 }
param { lr_mult: 2 }
inner_product_param {
num_output: 2 # origial is 21, class_num + 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}

layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param { lr_mult: 1 }
param { lr_mult: 2 }
inner_product_param {
num_output: 8 # original is 84, (class_num+1)*4
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}

2、修改py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_rpn_train.pt & stage2_rpn_train.pt

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': 2" # original is 21, class_num + 1
}
}

3、py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/faster_rcnn_test.pt

layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
inner_product_param {
num_output: 2 # original is 21, class_num + 1
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
inner_product_param {
num_output: 8 # original is 84, (class_num + 1)*4
}
}

4、py-faster-rcnn/lib/datasets/pascal_voc.py修改（ZF时已修改）

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
#'aeroplane', 'bicycle', 'bird', 'boat',
#'bottle', 'bus', 'car', 'cat', 'chair',
#'cow', 'diningtable', 'dog', 'horse',
#'motorbike', 'person', 'pottedplant',
#'sheep', 'sofa', 'train', 'tvmonitor'
'leftAtrial'
)

5、py-faster-rcnn/lib/datasets/imdb.py修改（ZF时已修改）

将append_flipped_images(self)函数的第二行widths = self._get_widths()改为如下形式：
widths = [PIL.Image.open(self.image_path_at(i)).size[0]
for i in xrange(num_images)]

6、修改tools/train_faster_rcnn_alt_opt.py中的迭代次数

max_iters = [8000, 4000, 8000, 4000]
修改models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/下对应的solver文件的stepsize（学习率等超参也在这里修改），要小于max_iters
stepsize: 3000 # original is 30000, should smaller than max_iters[1]#stage1_fast_rcnn_solver30k40k.pt
stepsize: 6000 # original is 60000, should smaller than max_iters[0]#stage1_rpn_solver60k80k.pt
stepsize: 3000 # original is 30000, should smaller than max_iters[3]#stage2_fast_rcnn_solver30k40k.pt
stepsize: 6000 # original is 60000, should smaller than max_iters[2]#stage2_rpn_solver60k80k.pt

将solver中第一行的路径改为绝对路径，否则会报找不到路径的错误

train_net: "/home/lys/py-faster-rcnn/models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt"

7、删除output以及/data/cache，py-faster-rcnn/data/VOCdevkit2007/annotation_cache（使用test_net.py测试时产生）将对应的文件放入/data/VOCdevkit2007/VOC2007/

8、训练：

python train_faster_rcnn_alt_opt.py  --net_name VGG_CNN_M_1024 --weights /home/lys/py-faster-rcnn/data/imagenet_models/VGG_CNN_M_1024.v2.caffemodel --cfg /home/lys/py-faster-rcnn/experiments/cfgs/faster_rcnn_alt_opt.yml  --imdb voc_2007_trainval

I0831 11:23:16.666177 22761 solver.cpp:229] Iteration 0, loss = 1.16274
I0831 11:23:16.666204 22761 solver.cpp:245]     Train net output #0: rpn_cls_loss = 0.689726 (* 1 = 0.689726 loss)
I0831 11:23:16.666209 22761 solver.cpp:245]     Train net output #1: rpn_loss_bbox = 0.473018 (* 1 = 0.473018 loss)
I0831 11:23:16.666214 22761 sgd_solver.cpp:106] Iteration 0, lr = 0.001
I0831 11:24:29.267117 22761 solver.cpp:229] Iterat
4000
ion 20, loss = 0.560839
I0831 11:24:29.267145 22761 solver.cpp:245]     Train net output #0: rpn_cls_loss = 0.495616 (* 1 = 0.495616 loss)
I0831 11:24:29.267151 22761 solver.cpp:245]     Train net output #1: rpn_loss_bbox = 0.0652227 (* 1 = 0.0652227 loss)

9、使用demo.py进行测试

需要加入NETS中加入'vgg_m':('VGG_CNN_M_1024',  'VGG_CNN_M_1024_faster_rcnn_final.caffemodel')，红色部分应该与/models/pascal_voc/下的VGG_CNN_M_1024文件名相同。

python demo.py --net vgg_m --cpu