Python版Faster-RCNN安装配置

本文参照github 编写，参考地址如下:

https://github.com/rbgirshick/py-faster-rcnn

一、 软件要求：

1，python必须支持python layers:

#  Makefile.config, make sure to have this line uncommented
WITH_PYTHON_LAYER := 1
# Unrelatedly, it's also recommended that you use CUDNN
USE_CUDNN := 1

2,python包必须包括:

cython, python-opencv, easydict

二、硬件要求：

1，对于小型网络的训练(ZF, VGG_CNN_M_1024)，一个有3G内存的好的gpu就可以了(e.g., Titan, K20, K40, …) 。

2，为了用VGG16寻训练fast-rcnn，我们需要一个 K40 (~11G of memory)。

3，用端到端(end to end)的方式训练用VGG16构建的Faster-Rcnn ,在使用CUDnn情况下，一个 K40 (~3G of memory)足够了。

三、安装

1， 从github上克隆faster-rcnn 源代码，注意必须采用命令行的方式下载，不要使用在浏览器内直接下载，不然会漏掉很多东西:

# Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git[/code] 
2,建立 Cpython模块：

cd $FRCN_ROOT/lib
make


3，建立Caffe 和 pycaffe：

cd $FRCN_ROOT/caffe-fast-rcnn
make -j8 && make pycaffe


注意：在编译的时候容易出现两种错误：

（1）， 由于cudnn版本不对，无法编译通过，在这里推荐在安装caffe时使用cudnn4.0版

（2），make过程中出现比如 string.h ‘memcy’ was not declared in this scope的错误是由于gcc编译器版本太新，解决方法是打开makefile搜索并替换：

NVCCFLAGS += -ccbin=$(CXX) -Xcompiler -fPIC $(COMMON_FLAGS)
为
NVCCFLAGS += -D_FORCE_INLINES -ccbin=$(CXX) -Xcompiler -fPIC $(COMMON_FLAGS)


当然，如果caffe正确安装，是不会出现这种问题的。

4，下载已经训练好的模型Faster R-CNN ：

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


这一步会在
$FRCN_ROOT/data
 文件夹下下载 生成faster_rcnn_models. 的压缩文件大概700M大小，解压缩后备用。

四、测试：

完成的基本的安装后用demo测试一下：

cd $FRCN_ROOT
./tools/demo.py


运行结果如下则表明安装成功：

/usr/lib/python2.7/dist-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.
warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0908 20:21:59.205785  4215 net.cpp:49] Initializing net from parameters:
name: "VGG_ILSVRC_16_layers"
input: "data"
input: "im_info"
state {
phase: TEST
}
input_shape {
dim: 1
dim: 3
dim: 224
dim: 224
}
input_shape {
dim: 1
dim: 3
}
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data"
top: "conv1_1"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
layer {
name: "relu1_1"
type: "ReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "conv1_2"
type: "Convolution"
bottom: "conv1_1"
top: "conv1_2"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
}
}
layer {
name: "relu1_2"
type: "ReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1_2"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2_1"
type: "Convolution"
bottom: "pool1"
top: "conv2_1"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
layer {
name: "relu2_1"
type: "ReLU"
bottom: "conv2_1"
top: "conv2_1"
}
layer {
name: "conv2_2"
type: "Convolution"
bottom: "conv2_1"
top: "conv2_2"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
}
}
layer {
name: "relu2_2"
type: "ReLU"
bottom: "conv2_2"
top: "conv2_2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2_2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv3_1"
type: "Convolution"
bottom: "pool2"
top: "conv3_1"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3_1"
type: "ReLU"
bottom: "conv3_1"
top: "conv3_1"
}
layer {
name: "conv3_2"
type: "Convolution"
bottom: "conv3_1"
top: "conv3_2"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3_2"
type: "ReLU"
bottom: "conv3_2"
top: "conv3_2"
}
layer {
name: "conv3_3"
type: "Convolution"
bottom: "conv3_2"
top: "conv3_3"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3_3"
type: "ReLU"
bottom: "conv3_3"
top: "conv3_3"
}
layer {
name: "pool3"
type: "Pooling"
bottom: "conv3_3"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv4_1"
type: "Convolution"
bottom: "pool3"
top: "conv4_1"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu4_1"
type: "ReLU"
bottom: "conv4_1"
top: "conv4_1"
}
layer {
name: "conv4_2"
type: "Convolution"
bottom: "conv4_1"
top: "conv4_2"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu4_2"
type: "ReLU"
bottom: "conv4_2"
top: "conv4_2"
}
layer {
name: "conv4_3"
type: "Convolution"
bottom: "conv4_2"
top: "conv4_3"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu4_3"
type: "ReLU"
bottom: "conv4_3"
top: "conv4_3"
}
layer {
name: "pool4"
type: "Pooling"
bottom: "conv4_3"
top: "pool4"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv5_1"
type: "Convolution"
bottom: "pool4"
top: "conv5_1"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu5_1"
type: "ReLU"
bottom: "conv5_1"
top: "conv5_1"
}
layer {
name: "conv5_2"
type: "Convolution"
bottom: "conv5_1"
top: "conv5_2"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu5_2"
type: "ReLU"
bottom: "conv5_2"
top: "conv5_2"
}
layer {
name: "conv5_3"
type: "Convolution"
bottom: "conv5_2"
top: "conv5_3"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
}
}
layer {
name: "relu5_3"
type: "ReLU"
bottom: "conv5_3"
top: "conv5_3"
}
layer {
name: "rpn_conv/3x3"
type: "Convolution"
bottom: "conv5_3"
top: "rpn/output"
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "rpn_relu/3x3"
type: "ReLU"
bottom: "rpn/output"
top: "rpn/output"
}
layer {
name: "rpn_cls_score"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_cls_score"
convolution_param {
num_output: 18
pad: 0
kernel_size: 1
stride: 1
}
}
layer {
name: "rpn_bbox_pred"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_bbox_pred"
convolution_param {
num_output: 36
pad: 0
kernel_size: 1
stride: 1
}
}
layer {
name: "rpn_cls_score_reshape"
type: "Reshape"
bottom: "rpn_cls_score"
top: "rpn_cls_score_reshape"
reshape_param {
shape {
dim: 0
dim: 2
dim: -1
dim: 0
}
}
}
layer {
name: "rpn_cls_prob"
type: "Softmax"
bottom: "rpn_cls_score_reshape"
top: "rpn_cls_prob"
}
layer {
name: "rpn_cls_prob_reshape"
type: "Reshape"
bottom: "rpn_cls_prob"
top: "rpn_cls_prob_reshape"
reshape_param {
shape {
dim: 0
dim: 18
dim: -1
dim: 0
}
}
}
layer {
name: "proposal"
type: "Python"
bottom: "rpn_cls_prob_reshape"
bottom: "rpn_bbox_pred"
bottom: "im_info"
top: "rois"
python_param {
module: "rpn.proposal_layer"
layer: "ProposalLayer"
param_str: "\'feat_stride\': 16"
}
}
layer {
name: "roi_pool5"
type: "ROIPooling"
bottom: "conv5_3"
bottom: "rois"
top: "pool5"
roi_pooling_param {
pooled_h: 7
pooled_w: 7
spatial_scale: 0.0625
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
inner_product_param {
num_output: 21
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
inner_product_param {
num_output: 84
}
}
layer {
name: "cls_prob"
type: "Softmax"
bottom: "cls_score"
top: "cls_prob"
}
I0908 20:21:59.206061  4215 net.cpp:413] Input 0 -> data
I0908 20:21:59.309164  4215 net.cpp:413] Input 1 -> im_info
I0908 20:21:59.309209  4215 layer_factory.hpp:77] Creating layer conv1_1
I0908 20:21:59.309229  4215 net.cpp:106] Creating Layer conv1_1
I0908 20:21:59.309232  4215 net.cpp:454] conv1_1 <- data
I0908 20:21:59.309237  4215 net.cpp:411] conv1_1 -> conv1_1
I0908 20:22:00.151002  4215 net.cpp:150] Setting up conv1_1
I0908 20:22:00.151026  4215 net.cpp:157] Top shape: 1 64 224 224 (3211264)
I0908 20:22:00.151029  4215 net.cpp:165] Memory required for data: 12845056
I0908 20:22:00.151042  4215 layer_factory.hpp:77] Creating layer relu1_1
I0908 20:22:00.151053  4215 net.cpp:106] Creating Layer relu1_1
I0908 20:22:00.151057  4215 net.cpp:454] relu1_1 <- conv1_1
I0908 20:22:00.151062  4215 net.cpp:397] relu1_1 -> conv1_1 (in-place)
I0908 20:22:00.151320  4215 net.cpp:150] Setting up relu1_1
I0908 20:22:00.151327  4215 net.cpp:157] Top shape: 1 64 224 224 (3211264)
I0908 20:22:00.151329  4215 net.cpp:165] Memory required for data: 25690112
I0908 20:22:00.151331  4215 layer_factory.hpp:77] Creating layer conv1_2
I0908 20:22:00.151340  4215 net.cpp:106] Creating Layer conv1_2
I0908 20:22:00.151342  4215 net.cpp:454] conv1_2 <- conv1_1
I0908 20:22:00.151347  4215 net.cpp:411] conv1_2 -> conv1_2
I0908 20:22:00.152340  4215 net.cpp:150] Setting up conv1_2
I0908 20:22:00.152350  4215 net.cpp:157] Top shape: 1 64 224 224 (3211264)
I0908 20:22:00.152354  4215 net.cpp:165] Memory required for data: 38535168
I0908 20:22:00.152359  4215 layer_factory.hpp:77] Creating layer relu1_2
I0908 20:22:00.152364  4215 net.cpp:106] Creating Layer relu1_2
I0908 20:22:00.152367  4215 net.cpp:454] relu1_2 <- conv1_2
I0908 20:22:00.152371  4215 net.cpp:397] relu1_2 -> conv1_2 (in-place)
I0908 20:22:00.152498  4215 net.cpp:150] Setting up relu1_2
I0908 20:22:00.152503  4215 net.cpp:157] Top shape: 1 64 224 224 (3211264)
I0908 20:22:00.152504  4215 net.cpp:165] Memory required for data: 51380224
I0908 20:22:00.152506  4215 layer_factory.hpp:77] Creating layer pool1
I0908 20:22:00.152513  4215 net.cpp:106] Creating Layer pool1
I0908 20:22:00.152513  4215 net.cpp:454] pool1 <- conv1_2
I0908 20:22:00.152518  4215 net.cpp:411] pool1 -> pool1
I0908 20:22:00.152549  4215 net.cpp
1b5d8
:150] Setting up pool1
I0908 20:22:00.152552  4215 net.cpp:157] Top shape: 1 64 112 112 (802816)
I0908 20:22:00.152554  4215 net.cpp:165] Memory required for data: 54591488
I0908 20:22:00.152555  4215 layer_factory.hpp:77] Creating layer conv2_1
I0908 20:22:00.152561  4215 net.cpp:106] Creating Layer conv2_1
I0908 20:22:00.152564  4215 net.cpp:454] conv2_1 <- pool1
I0908 20:22:00.152566  4215 net.cpp:411] conv2_1 -> conv2_1
I0908 20:22:00.154081  4215 net.cpp:150] Setting up conv2_1
I0908 20:22:00.154090  4215 net.cpp:157] Top shape: 1 128 112 112 (1605632)
I0908 20:22:00.154093  4215 net.cpp:165] Memory required for data: 61014016
I0908 20:22:00.154098  4215 layer_factory.hpp:77] Creating layer relu2_1
I0908 20:22:00.154103  4215 net.cpp:106] Creating Layer relu2_1
I0908 20:22:00.154105  4215 net.cpp:454] relu2_1 <- conv2_1
I0908 20:22:00.154110  4215 net.cpp:397] relu2_1 -> conv2_1 (in-place)
I0908 20:22:00.154381  4215 net.cpp:150] Setting up relu2_1
I0908 20:22:00.154388  4215 net.cpp:157] Top shape: 1 128 112 112 (1605632)
I0908 20:22:00.154391  4215 net.cpp:165] Memory required for data: 67436544
I0908 20:22:00.154392  4215 layer_factory.hpp:77] Creating layer conv2_2
I0908 20:22:00.154398  4215 net.cpp:106] Creating Layer conv2_2
I0908 20:22:00.154402  4215 net.cpp:454] conv2_2 <- conv2_1
I0908 20:22:00.154405  4215 net.cpp:411] conv2_2 -> conv2_2
I0908 20:22:00.155148  4215 net.cpp:150] Setting up conv2_2
I0908 20:22:00.155155  4215 net.cpp:157] Top shape: 1 128 112 112 (1605632)
I0908 20:22:00.155158  4215 net.cpp:165] Memory required for data: 73859072
I0908 20:22:00.155163  4215 layer_factory.hpp:77] Creating layer relu2_2
I0908 20:22:00.155167  4215 net.cpp:106] Creating Layer relu2_2
I0908 20:22:00.155170  4215 net.cpp:454] relu2_2 <- conv2_2
I0908 20:22:00.155175  4215 net.cpp:397] relu2_2 -> conv2_2 (in-place)
I0908 20:22:00.155441  4215 net.cpp:150] Setting up relu2_2
I0908 20:22:00.155449  4215 net.cpp:157] Top shape: 1 128 112 112 (1605632)
I0908 20:22:00.155452  4215 net.cpp:165] Memory required for data: 80281600
I0908 20:22:00.155453  4215 layer_factory.hpp:77] Creating layer pool2
I0908 20:22:00.155457  4215 net.cpp:106] Creating Layer pool2
I0908 20:22:00.155459  4215 net.cpp:454] pool2 <- conv2_2
I0908 20:22:00.155463  4215 net.cpp:411] pool2 -> pool2
I0908 20:22:00.155493  4215 net.cpp:150] Setting up pool2
I0908 20:22:00.155496  4215 net.cpp:157] Top shape: 1 128 56 56 (401408)
I0908 20:22:00.155498  4215 net.cpp:165] Memory required for data: 81887232
I0908 20:22:00.155500  4215 layer_factory.hpp:77] Creating layer conv3_1
I0908 20:22:00.155504  4215 net.cpp:106] Creating Layer conv3_1
I0908 20:22:00.155506  4215 net.cpp:454] conv3_1 <- pool2
I0908 20:22:00.155510  4215 net.cpp:411] conv3_1 -> conv3_1
I0908 20:22:00.156734  4215 net.cpp:150] Setting up conv3_1
I0908 20:22:00.156743  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.156744  4215 net.cpp:165] Memory required for data: 85098496
I0908 20:22:00.156749  4215 layer_factory.hpp:77] Creating layer relu3_1
I0908 20:22:00.156754  4215 net.cpp:106] Creating Layer relu3_1
I0908 20:22:00.156756  4215 net.cpp:454] relu3_1 <- conv3_1
I0908 20:22:00.156761  4215 net.cpp:397] relu3_1 -> conv3_1 (in-place)
I0908 20:22:00.156880  4215 net.cpp:150] Setting up relu3_1
I0908 20:22:00.156886  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.156888  4215 net.cpp:165] Memory required for data: 88309760
I0908 20:22:00.156889  4215 layer_factory.hpp:77] Creating layer conv3_2
I0908 20:22:00.156894  4215 net.cpp:106] Creating Layer conv3_2
I0908 20:22:00.156896  4215 net.cpp:454] conv3_2 <- conv3_1
I0908 20:22:00.156901  4215 net.cpp:411] conv3_2 -> conv3_2
I0908 20:22:00.167906  4215 net.cpp:150] Setting up conv3_2
I0908 20:22:00.167923  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.167925  4215 net.cpp:165] Memory required for data: 91521024
I0908 20:22:00.167932  4215 layer_factory.hpp:77] Creating layer relu3_2
I0908 20:22:00.167939  4215 net.cpp:106] Creating Layer relu3_2
I0908 20:22:00.167943  4215 net.cpp:454] relu3_2 <- conv3_2
I0908 20:22:00.167948  4215 net.cpp:397] relu3_2 -> conv3_2 (in-place)
I0908 20:22:00.168265  4215 net.cpp:150] Setting up relu3_2
I0908 20:22:00.168273  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.168275  4215 net.cpp:165] Memory required for data: 94732288
I0908 20:22:00.168278  4215 layer_factory.hpp:77] Creating layer conv3_3
I0908 20:22:00.168287  4215 net.cpp:106] Creating Layer conv3_3
I0908 20:22:00.168289  4215 net.cpp:454] conv3_3 <- conv3_2
I0908 20:22:00.168293  4215 net.cpp:411] conv3_3 -> conv3_3
I0908 20:22:00.169926  4215 net.cpp:150] Setting up conv3_3
I0908 20:22:00.169934  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.169936  4215 net.cpp:165] Memory required for data: 97943552
I0908 20:22:00.169940  4215 layer_factory.hpp:77] Creating layer relu3_3
I0908 20:22:00.169945  4215 net.cpp:106] Creating Layer relu3_3
I0908 20:22:00.169947  4215 net.cpp:454] relu3_3 <- conv3_3
I0908 20:22:00.169950  4215 net.cpp:397] relu3_3 -> conv3_3 (in-place)
I0908 20:22:00.170212  4215 net.cpp:150] Setting up relu3_3
I0908 20:22:00.170219  4215 net.cpp:157] Top shape: 1 256 56 56 (802816)
I0908 20:22:00.170222  4215 net.cpp:165] Memory required for data: 101154816
I0908 20:22:00.170223  4215 layer_factory.hpp:77] Creating layer pool3
I0908 20:22:00.170231  4215 net.cpp:106] Creating Layer pool3
I0908 20:22:00.170234  4215 net.cpp:454] pool3 <- conv3_3
I0908 20:22:00.170238  4215 net.cpp:411] pool3 -> pool3
I0908 20:22:00.170269  4215 net.cpp:150] Setting up pool3
I0908 20:22:00.170274  4215 net.cpp:157] Top shape: 1 256 28 28 (200704)
I0908 20:22:00.170274  4215 net.cpp:165] Memory required for data: 101957632
I0908 20:22:00.170276  4215 layer_factory.hpp:77] Creating layer conv4_1
I0908 20:22:00.170281  4215 net.cpp:106] Creating Layer conv4_1
I0908 20:22:00.170284  4215 net.cpp:454] conv4_1 <- pool3
I0908 20:22:00.170285  4215 net.cpp:411] conv4_1 -> conv4_1
I0908 20:22:00.172976  4215 net.cpp:150] Setting up conv4_1
I0908 20:22:00.172994  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.172997  4215 net.cpp:165] Memory required for data: 103563264
I0908 20:22:00.173003  4215 layer_factory.hpp:77] Creating layer relu4_1
I0908 20:22:00.173010  4215 net.cpp:106] Creating Layer relu4_1
I0908 20:22:00.173013  4215 net.cpp:454] relu4_1 <- conv4_1
I0908 20:22:00.173018  4215 net.cpp:397] relu4_1 -> conv4_1 (in-place)
I0908 20:22:00.173144  4215 net.cpp:150] Setting up relu4_1
I0908 20:22:00.173151  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.173151  4215 net.cpp:165] Memory required for data: 105168896
I0908 20:22:00.173153  4215 layer_factory.hpp:77] Creating layer conv4_2
I0908 20:22:00.173159  4215 net.cpp:106] Creating Layer conv4_2
I0908 20:22:00.173162  4215 net.cpp:454] conv4_2 <- conv4_1
I0908 20:22:00.173166  4215 net.cpp:411] conv4_2 -> conv4_2
I0908 20:22:00.178277  4215 net.cpp:150] Setting up conv4_2
I0908 20:22:00.178311  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.178314  4215 net.cpp:165] Memory required for data: 106774528
I0908 20:22:00.178331  4215 layer_factory.hpp:77] Creating layer relu4_2
I0908 20:22:00.178349  4215 net.cpp:106] Creating Layer relu4_2
I0908 20:22:00.178354  4215 net.cpp:454] relu4_2 <- conv4_2
I0908 20:22:00.178359  4215 net.cpp:397] relu4_2 -> conv4_2 (in-place)
I0908 20:22:00.178628  4215 net.cpp:150] Setting up relu4_2
I0908 20:22:00.178637  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.178638  4215 net.cpp:165] Memory required for data: 108380160
I0908 20:22:00.178640  4215 layer_factory.hpp:77] Creating layer conv4_3
I0908 20:22:00.178647  4215 net.cpp:106] Creating Layer conv4_3
I0908 20:22:00.178649  4215 net.cpp:454] conv4_3 <- conv4_2
I0908 20:22:00.178654  4215 net.cpp:411] conv4_3 -> conv4_3
I0908 20:22:00.183998  4215 net.cpp:150] Setting up conv4_3
I0908 20:22:00.184022  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.184026  4215 net.cpp:165] Memory required for data: 109985792
I0908 20:22:00.184043  4215 layer_factory.hpp:77] Creating layer relu4_3
I0908 20:22:00.184052  4215 net.cpp:106] Creating Layer relu4_3
I0908 20:22:00.184056  4215 net.cpp:454] relu4_3 <- conv4_3
I0908 20:22:00.184063  4215 net.cpp:397] relu4_3 -> conv4_3 (in-place)
I0908 20:22:00.184335  4215 net.cpp:150] Setting up relu4_3
I0908 20:22:00.184342  4215 net.cpp:157] Top shape: 1 512 28 28 (401408)
I0908 20:22:00.184345  4215 net.cpp:165] Memory required for data: 111591424
I0908 20:22:00.184357  4215 layer_factory.hpp:77] Creating layer pool4
I0908 20:22:00.184365  4215 net.cpp:106] Creating Layer pool4
I0908 20:22:00.184366  4215 net.cpp:454] pool4 <- conv4_3
I0908 20:22:00.184370  4215 net.cpp:411] pool4 -> pool4
I0908 20:22:00.184412  4215 net.cpp:150] Setting up pool4
I0908 20:22:00.184415  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.184417  4215 net.cpp:165] Memory required for data: 111992832
I0908 20:22:00.184429  4215 layer_factory.hpp:77] Creating layer conv5_1
I0908 20:22:00.184437  4215 net.cpp:106] Creating Layer conv5_1
I0908 20:22:00.184439  4215 net.cpp:454] conv5_1 <- pool4
I0908 20:22:00.184442  4215 net.cpp:411] conv5_1 -> conv5_1
I0908 20:22:00.189421  4215 net.cpp:150] Setting up conv5_1
I0908 20:22:00.189446  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.189460  4215 net.cpp:165] Memory required for data: 112394240
I0908 20:22:00.189467  4215 layer_factory.hpp:77] Creating layer relu5_1
I0908 20:22:00.189477  4215 net.cpp:106] Creating Layer relu5_1
I0908 20:22:00.189481  4215 net.cpp:454] relu5_1 <- conv5_1
I0908 20:22:00.189487  4215 net.cpp:397] relu5_1 -> conv5_1 (in-place)
I0908 20:22:00.189631  4215 net.cpp:150] Setting up relu5_1
I0908 20:22:00.189637  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.189640  4215 net.cpp:165] Memory required for data: 112795648
I0908 20:22:00.189642  4215 layer_factory.hpp:77] Creating layer conv5_2
I0908 20:22:00.189649  4215 net.cpp:106] Creating Layer conv5_2
I0908 20:22:00.189652  4215 net.cpp:454] conv5_2 <- conv5_1
I0908 20:22:00.189656  4215 net.cpp:411] conv5_2 -> conv5_2
I0908 20:22:00.194391  4215 net.cpp:150] Setting up conv5_2
I0908 20:22:00.194420  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.194433  4215 net.cpp:165] Memory required for data: 113197056
I0908 20:22:00.194443  4215 layer_factory.hpp:77] Creating layer relu5_2
I0908 20:22:00.194453  4215 net.cpp:106] Creating Layer relu5_2
I0908 20:22:00.194456  4215 net.cpp:454] relu5_2 <- conv5_2
I0908 20:22:00.194463  4215 net.cpp:397] relu5_2 -> conv5_2 (in-place)
I0908 20:22:00.194744  4215 net.cpp:150] Setting up relu5_2
I0908 20:22:00.194751  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.194754  4215 net.cpp:165] Memory required for data: 113598464
I0908 20:22:00.194756  4215 layer_factory.hpp:77] Creating layer conv5_3
I0908 20:22:00.194764  4215 net.cpp:106] Creating Layer conv5_3
I0908 20:22:00.194767  4215 net.cpp:454] conv5_3 <- conv5_2
I0908 20:22:00.194772  4215 net.cpp:411] conv5_3 -> conv5_3
I0908 20:22:00.199458  4215 net.cpp:150] Setting up conv5_3
I0908 20:22:00.199486  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.199489  4215 net.cpp:165] Memory required for data: 113999872
I0908 20:22:00.199508  4215 layer_factory.hpp:77] Creating layer relu5_3
I0908 20:22:00.199518  4215 net.cpp:106] Creating Layer relu5_3
I0908 20:22:00.199522  4215 net.cpp:454] relu5_3 <- conv5_3
I0908 20:22:00.199528  4215 net.cpp:397] relu5_3 -> conv5_3 (in-place)
I0908 20:22:00.199827  4215 net.cpp:150] Setting up relu5_3
I0908 20:22:00.199834  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.199836  4215 net.cpp:165] Memory required for data: 114401280
I0908 20:22:00.199839  4215 layer_factory.hpp:77] Creating layer conv5_3_relu5_3_0_split
I0908 20:22:00.199844  4215 net.cpp:106] Creating Layer conv5_3_relu5_3_0_split
I0908 20:22:00.199847  4215 net.cpp:454] conv5_3_relu5_3_0_split <- conv5_3
I0908 20:22:00.199852  4215 net.cpp:411] conv5_3_relu5_3_0_split -> conv5_3_relu5_3_0_split_0
I0908 20:22:00.199857  4215 net.cpp:411] conv5_3_relu5_3_0_split -> conv5_3_relu5_3_0_split_1
I0908 20:22:00.199890  4215 net.cpp:150] Setting up conv5_3_relu5_3_0_split
I0908 20:22:00.199894  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.199898  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.199899  4215 net.cpp:165] Memory required for data: 115204096
I0908 20:22:00.199901  4215 layer_factory.hpp:77] Creating layer rpn_conv/3x3
I0908 20:22:00.199908  4215 net.cpp:106] Creating Layer rpn_conv/3x3
I0908 20:22:00.199911  4215 net.cpp:454] rpn_conv/3x3 <- conv5_3_relu5_3_0_split_0
I0908 20:22:00.199915  4215 net.cpp:411] rpn_conv/3x3 -> rpn/output
I0908 20:22:00.204633  4215 net.cpp:150] Setting up rpn_conv/3x3
I0908 20:22:00.204661  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.204664  4215 net.cpp:165] Memory required for data: 115605504
I0908 20:22:00.204682  4215 layer_factory.hpp:77] Creating layer rpn_relu/3x3
I0908 20:22:00.204699  4215 net.cpp:106] Creating Layer rpn_relu/3x3
I0908 20:22:00.204702  4215 net.cpp:454] rpn_relu/3x3 <- rpn/output
I0908 20:22:00.204710  4215 net.cpp:397] rpn_relu/3x3 -> rpn/output (in-place)
I0908 20:22:00.204839  4215 net.cpp:150] Setting up rpn_relu/3x3
I0908 20:22:00.204845  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.204848  4215 net.cpp:165] Memory required for data: 116006912
I0908 20:22:00.204859  4215 layer_factory.hpp:77] Creating layer rpn/output_rpn_relu/3x3_0_split
I0908 20:22:00.204865  4215 net.cpp:106] Creating Layer rpn/output_rpn_relu/3x3_0_split
I0908 20:22:00.204867  4215 net.cpp:454] rpn/output_rpn_relu/3x3_0_split <- rpn/output
I0908 20:22:00.204871  4215 net.cpp:411] rpn/output_rpn_relu/3x3_0_split -> rpn/output_rpn_relu/3x3_0_split_0
I0908 20:22:00.204876  4215 net.cpp:411] rpn/output_rpn_relu/3x3_0_split -> rpn/output_rpn_relu/3x3_0_split_1
I0908 20:22:00.204918  4215 net.cpp:150] Setting up rpn/output_rpn_relu/3x3_0_split
I0908 20:22:00.204922  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.204926  4215 net.cpp:157] Top shape: 1 512 14 14 (100352)
I0908 20:22:00.204927  4215 net.cpp:165] Memory required for data: 116809728
I0908 20:22:00.204939  4215 layer_factory.hpp:77] Creating layer rpn_cls_score
I0908 20:22:00.204946  4215 net.cpp:106] Creating Layer rpn_cls_score
I0908 20:22:00.204949  4215 net.cpp:454] rpn_cls_score <- rpn/output_rpn_relu/3x3_0_split_0
I0908 20:22:00.204953  4215 net.cpp:411] rpn_cls_score -> rpn_cls_score
I0908 20:22:00.205927  4215 net.cpp:150] Setting up rpn_cls_score
I0908 20:22:00.205935  4215 net.cpp:157] Top shape: 1 18 14 14 (3528)
I0908 20:22:00.205948  4215 net.cpp:165] Memory required for data: 116823840
I0908 20:22:00.205952  4215 layer_factory.hpp:77] Creating layer rpn_bbox_pred
I0908 20:22:00.205960  4215 net.cpp:106] Creating Layer rpn_bbox_pred
I0908 20:22:00.205962  4215 net.cpp:454] rpn_bbox_pred <- rpn/output_rpn_relu/3x3_0_split_1
I0908 20:22:00.205966  4215 net.cpp:411] rpn_bbox_pred -> rpn_bbox_pred
I0908 20:22:00.206796  4215 net.cpp:150] Setting up rpn_bbox_pred
I0908 20:22:00.206804  4215 net.cpp:157] Top shape: 1 36 14 14 (7056)
I0908 20:22:00.206806  4215 net.cpp:165] Memory required for data: 116852064
I0908 20:22:00.206821  4215 layer_factory.hpp:77] Creating layer rpn_cls_score_reshape
I0908 20:22:00.206827  4215 net.cpp:106] Creating Layer rpn_cls_score_reshape
I0908 20:22:00.206830  4215 net.cpp:454] rpn_cls_score_reshape <- rpn_cls_score
I0908 20:22:00.206835  4215 net.cpp:411] rpn_cls_score_reshape -> rpn_cls_score_reshape
I0908 20:22:00.206856  4215 net.cpp:150] Setting up rpn_cls_score_reshape
I0908 20:22:00.206869  4215 net.cpp:157] Top shape: 1 2 126 14 (3528)
I0908 20:22:00.206871  4215 net.cpp:165] Memory required for data: 116866176
I0908 20:22:00.206873  4215 layer_factory.hpp:77] Creating layer rpn_cls_prob
I0908 20:22:00.206889  4215 net.cpp:106] Creating Layer rpn_cls_prob
I0908 20:22:00.206892  4215 net.cpp:454] rpn_cls_prob <- rpn_cls_score_reshape
I0908 20:22:00.206895  4215 net.cpp:411] rpn_cls_prob -> rpn_cls_prob
I0908 20:22:00.207056  4215 net.cpp:150] Setting up rpn_cls_prob
I0908 20:22:00.207061  4215 net.cpp:157] Top shape: 1 2 126 14 (3528)
I0908 20:22:00.207063  4215 net.cpp:165] Memory required for data: 116880288
I0908 20:22:00.207077  4215 layer_factory.hpp:77] Creating layer rpn_cls_prob_reshape
I0908 20:22:00.207082  4215 net.cpp:106] Creating Layer rpn_cls_prob_reshape
I0908 20:22:00.207083  4215 net.cpp:454] rpn_cls_prob_reshape <- rpn_cls_prob
I0908 20:22:00.207087  4215 net.cpp:411] rpn_cls_prob_reshape -> rpn_cls_prob_reshape
I0908 20:22:00.207105  4215 net.cpp:150] Setting up rpn_cls_prob_reshape
I0908 20:22:00.207109  4215 net.cpp:157] Top shape: 1 18 14 14 (3528)
I0908 20:22:00.207120  4215 net.cpp:165] Memory required for data: 116894400
I0908 20:22:00.207123  4215 layer_factory.hpp:77] Creating layer proposal
I0908 20:22:00.257710  4215 net.cpp:106] Creating Layer proposal
I0908 20:22:00.257730  4215 net.cpp:454] proposal <- rpn_cls_prob_reshape
I0908 20:22:00.257735  4215 net.cpp:454] proposal <- rpn_bbox_pred
I0908 20:22:00.257737  4215 net.cpp:454] proposal <- im_info
I0908 20:22:00.257742  4215 net.cpp:411] proposal -> rois
I0908 20:22:00.258290  4215 net.cpp:150] Setting up proposal
I0908 20:22:00.258301  4215 net.cpp:157] Top shape: 1 5 (5)
I0908 20:22:00.258303  4215 net.cpp:165] Memory required for data: 116894420
I0908 20:22:00.258306  4215 layer_factory.hpp:77] Creating layer roi_pool5
I0908 20:22:00.258312  4215 net.cpp:106] Creating Layer roi_pool5
I0908 20:22:00.258316  4215 net.cpp:454] roi_pool5 <- conv5_3_relu5_3_0_split_1
I0908 20:22:00.258319  4215 net.cpp:454] roi_pool5 <- rois
I0908 20:22:00.258324  4215 net.cpp:411] roi_pool5 -> pool5
I0908 20:22:00.258330  4215 roi_pooling_layer.cpp:30] Spatial scale: 0.0625
I0908 20:22:00.258370  4215 net.cpp:150] Setting up roi_pool5
I0908 20:22:00.258374  4215 net.cpp:157] Top shape: 1 512 7 7 (25088)
I0908 20:22:00.258375  4215 net.cpp:165] Memory required for data: 116994772
I0908 20:22:00.258378  4215 layer_factory.hpp:77] Creating layer fc6
I0908 20:22:00.258383  4215 net.cpp:106] Creating Layer fc6
I0908 20:22:00.258384  4215 net.cpp:454] fc6 <- pool5
I0908 20:22:00.258388  4215 net.cpp:411] fc6 -> fc6
I0908 20:22:00.430316  4215 net.cpp:150] Setting up fc6
I0908 20:22:00.430344  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.430346  4215 net.cpp:165] Memory required for data: 117011156
I0908 20:22:00.430366  4215 layer_factory.hpp:77] Creating layer relu6
I0908 20:22:00.430389  4215 net.cpp:106] Creating Layer relu6
I0908 20:22:00.430393  4215 net.cpp:454] relu6 <- fc6
I0908 20:22:00.430398  4215 net.cpp:397] relu6 -> fc6 (in-place)
I0908 20:22:00.430800  4215 net.cpp:150] Setting up relu6
I0908 20:22:00.430807  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.430809  4215 net.cpp:165] Memory required for data: 117027540
I0908 20:22:00.430811  4215 layer_factory.hpp:77] Creating layer fc7
I0908 20:22:00.430815  4215 net.cpp:106] Creating Layer fc7
I0908 20:22:00.430817  4215 net.cpp:454] fc7 <- fc6
I0908 20:22:00.430821  4215 net.cpp:411] fc7 -> fc7
I0908 20:22:00.460335  4215 net.cpp:150] Setting up fc7
I0908 20:22:00.460360  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.460362  4215 net.cpp:165] Memory required for data: 117043924
I0908 20:22:00.460386  4215 layer_factory.hpp:77] Creating layer relu7
I0908 20:22:00.460404  4215 net.cpp:106] Creating Layer relu7
I0908 20:22:00.460408  4215 net.cpp:454] relu7 <- fc7
I0908 20:22:00.460423  4215 net.cpp:397] relu7 -> fc7 (in-place)
I0908 20:22:00.460865  4215 net.cpp:150] Setting up relu7
I0908 20:22:00.460871  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.460875  4215 net.cpp:165] Memory required for data: 117060308
I0908 20:22:00.460877  4215 layer_factory.hpp:77] Creating layer fc7_relu7_0_split
I0908 20:22:00.460893  4215 net.cpp:106] Creating Layer fc7_relu7_0_split
I0908 20:22:00.460896  4215 net.cpp:454] fc7_relu7_0_split <- fc7
I0908 20:22:00.460901  4215 net.cpp:411] fc7_relu7_0_split -> fc7_relu7_0_split_0
I0908 20:22:00.460906  4215 net.cpp:411] fc7_relu7_0_split -> fc7_relu7_0_split_1
I0908 20:22:00.460945  4215 net.cpp:150] Setting up fc7_relu7_0_split
I0908 20:22:00.460948  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.460952  4215 net.cpp:157] Top shape: 1 4096 (4096)
I0908 20:22:00.460952  4215 net.cpp:165] Memory required for data: 117093076
I0908 20:22:00.460954  4215 layer_factory.hpp:77] Creating layer cls_score
I0908 20:22:00.460958  4215 net.cpp:106] Creating Layer cls_score
I0908 20:22:00.460960  4215 net.cpp:454] cls_score <- fc7_relu7_0_split_0
I0908 20:22:00.460964  4215 net.cpp:411] cls_score -> cls_score
I0908 20:22:00.461432  4215 net.cpp:150] Setting up cls_score
I0908 20:22:00.461439  4215 net.cpp:157] Top shape: 1 21 (21)
I0908 20:22:00.461441  4215 net.cpp:165] Memory required for data: 117093160
I0908 20:22:00.461457  4215 layer_factory.hpp:77] Creating layer bbox_pred
I0908 20:22:00.461462  4215 net.cpp:106] Creating Layer bbox_pred
I0908 20:22:00.461463  4215 net.cpp:454] bbox_pred <- fc7_relu7_0_split_1
I0908 20:22:00.461467  4215 net.cpp:411] bbox_pred -> bbox_pred
I0908 20:22:00.462003  4215 net.cpp:150] Setting up bbox_pred
I0908 20:22:00.462010  4215 net.cpp:157] Top shape: 1 84 (84)
I0908 20:22:00.462013  4215 net.cpp:165] Memory required for data: 117093496
I0908 20:22:00.462030  4215 layer_factory.hpp:77] Creating layer cls_prob
I0908 20:22:00.462035  4215 net.cpp:106] Creating Layer cls_prob
I0908 20:22:00.462038  4215 net.cpp:454] cls_prob <- cls_score
I0908 20:22:00.462041  4215 net.cpp:411] cls_prob -> cls_prob
I0908 20:22:00.462208  4215 net.cpp:150] Setting up cls_prob
I0908 20:22:00.462213  4215 net.cpp:157] Top shape: 1 21 (21)
I0908 20:22:00.462215  4215 net.cpp:165] Memory required for data: 117093580
I0908 20:22:00.462229  4215 net.cpp:228] cls_prob does not need backward computation.
I0908 20:22:00.462231  4215 net.cpp:228] bbox_pred does not need backward computation.
I0908 20:22:00.462234  4215 net.cpp:228] cls_score does not need backward computation.
I0908 20:22:00.462236  4215 net.cpp:228] fc7_relu7_0_split does not need backward computation.
I0908 20:22:00.462239  4215 net.cpp:228] relu7 does not need backward computation.
I0908 20:22:00.462242  4215 net.cpp:228] fc7 does not need backward computation.
I0908 20:22:00.462255  4215 net.cpp:228] relu6 does not need backward computation.
I0908 20:22:00.462257  4215 net.cpp:228] fc6 does not need backward computation.
I0908 20:22:00.462260  4215 net.cpp:228] roi_pool5 does not need backward computation.
I0908 20:22:00.462263  4215 net.cpp:228] proposal does not need backward computation.
I0908 20:22:00.462267  4215 net.cpp:228] rpn_cls_prob_reshape does not need backward computation.
I0908 20:22:00.462270  4215 net.cpp:228] rpn_cls_prob does not need backward computation.
I0908 20:22:00.462273  4215 net.cpp:228] rpn_cls_score_reshape does not need backward computation.
I0908 20:22:00.462276  4215 net.cpp:228] rpn_bbox_pred does not need backward computation.
I0908 20:22:00.462280  4215 net.cpp:228] rpn_cls_score does not need
da99
backward computation.
I0908 20:22:00.462282  4215 net.cpp:228] rpn/output_rpn_relu/3x3_0_split does not need backward computation.
I0908 20:22:00.462285  4215 net.cpp:228] rpn_relu/3x3 does not need backward computation.
I0908 20:22:00.462288  4215 net.cpp:228] rpn_conv/3x3 does not need backward computation.
I0908 20:22:00.462291  4215 net.cpp:228] conv5_3_relu5_3_0_split does not need backward computation.
I0908 20:22:00.462294  4215 net.cpp:228] relu5_3 does not need backward computation.
I0908 20:22:00.462296  4215 net.cpp:228] conv5_3 does not need backward computation.
I0908 20:22:00.462299  4215 net.cpp:228] relu5_2 does not need backward computation.
I0908 20:22:00.462302  4215 net.cpp:228] conv5_2 does not need backward computation.
I0908 20:22:00.462306  4215 net.cpp:228] relu5_1 does not need backward computation.
I0908 20:22:00.462308  4215 net.cpp:228] conv5_1 does not need backward computation.
I0908 20:22:00.462311  4215 net.cpp:228] pool4 does not need backward computation.
I0908 20:22:00.462314  4215 net.cpp:228] relu4_3 does not need backward computation.
I0908 20:22:00.462316  4215 net.cpp:228] conv4_3 does not need backward computation.
I0908 20:22:00.462321  4215 net.cpp:228] relu4_2 does not need backward computation.
I0908 20:22:00.462323  4215 net.cpp:228] conv4_2 does not need backward computation.
I0908 20:22:00.462326  4215 net.cpp:228] relu4_1 does not need backward computation.
I0908 20:22:00.462328  4215 net.cpp:228] conv4_1 does not need backward computation.
I0908 20:22:00.462332  4215 net.cpp:228] pool3 does not need backward computation.
I0908 20:22:00.462334  4215 net.cpp:228] relu3_3 does not need backward computation.
I0908 20:22:00.462337  4215 net.cpp:228] conv3_3 does not need backward computation.
I0908 20:22:00.462339  4215 net.cpp:228] relu3_2 does not need backward computation.
I0908 20:22:00.462342  4215 net.cpp:228] conv3_2 does not need backward computation.
I0908 20:22:00.462344  4215 net.cpp:228] relu3_1 does not need backward computation.
I0908 20:22:00.462347  4215 net.cpp:228] conv3_1 does not need backward computation.
I0908 20:22:00.462350  4215 net.cpp:228] pool2 does not need backward computation.
I0908 20:22:00.462352  4215 net.cpp:228] relu2_2 does not need backward computation.
I0908 20:22:00.462355  4215 net.cpp:228] conv2_2 does not need backward computation.
I0908 20:22:00.462358  4215 net.cpp:228] relu2_1 does not need backward computation.
I0908 20:22:00.462360  4215 net.cpp:228] conv2_1 does not need backward computation.
I0908 20:22:00.462363  4215 net.cpp:228] pool1 does not need backward computation.
I0908 20:22:00.462365  4215 net.cpp:228] relu1_2 does not need backward computation.
I0908 20:22:00.462368  4215 net.cpp:228] conv1_2 does not need backward computation.
I0908 20:22:00.462370  4215 net.cpp:228] relu1_1 does not need backward computation.
I0908 20:22:00.462373  4215 net.cpp:228] conv1_1 does not need backward computation.
I0908 20:22:00.462375  4215 net.cpp:270] This network produces output bbox_pred
I0908 20:22:00.462378  4215 net.cpp:270] This network produces output cls_prob
I0908 20:22:00.462399  4215 net.cpp:283] Network initialization done.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:537] Reading dangerously large protocol message.  If the message turns out to be larger than 2147483647 bytes, parsing will be halted for security reasons.  To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 548317115
I0908 20:22:03.617671  4215 net.cpp:816] Ignoring source layer data
I0908 20:22:03.743860  4215 net.cpp:816] Ignoring source layer drop6
I0908 20:22:03.762300  4215 net.cpp:816] Ignoring source layer drop7
I0908 20:22:03.762327  4215 net.cpp:816] Ignoring source layer fc7_drop7_0_split
I0908 20:22:03.762817  4215 net.cpp:816] Ignoring source layer loss_cls
I0908 20:22:03.762821  4215 net.cpp:816] Ignoring source layer loss_bbox
I0908 20:22:03.765383  4215 net.cpp:816] Ignoring source layer silence_rpn_cls_score
I0908 20:22:03.765399  4215 net.cpp:816] Ignoring source layer silence_rpn_bbox_pred

Loaded network /home/panyiming/py-faster-rcnn/data/faster_rcnn_models/VGG16_faster_rcnn_final.caffemodel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Demo for data/demo/000456.jpg
Detection took 0.904s for 300 object proposals
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Demo for data/demo/000542.jpg
Detection took 0.810s for 161 object proposals
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Demo for data/demo/001150.jpg
Detection took 0.890s for 194 object proposals
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Demo for data/demo/001763.jpg
Detection took 0.891s for 196 object proposals
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Demo for data/demo/004545.jpg
Detection took 0.915s for 300 object proposals


运行完成后会出现 实例图片的探测结果。