caffe 训练与测试分类

1. 编译caffe
2.数据准备
3.网络文件准备，solver.prototxt resnet_50.prototxt ResNet-50-deploy.prototxt
4.训练指令
5.推理跑前向
6.三个完整网络文件

1. 编译caffe

编译caffe不用多说，网上好多教程，环境需要整好。
一般就是直接make
或者cmake编译

mkdir build
cd build
cmake ..
make -j8

2.数据准备

我喜欢直接用图片训练，简单直观，不用lmdb。
先制作train.txt和test.txt
txt里面放图片路径 label
例如：

/data2/hello/1.jpg 0
/data2/hello/1_23.jpg 1
/data2/hello/1_24.jpg 1

类别从0开始计数。

3.网络文件准备，solver.prototxt resnet_50.prototxt ResNet-50-deploy.prototxt

solver.prototxt

net: "/data_1/2022/my_net_test_2022/my_resnet_50.prototxt"
test_iter: 3000
test_interval: 3000
#test_initialization: true
display: 20
average_loss: 1000
base_lr: 0.0005  ##刚开始训练的学习率稍微放大一点0.01
lr_policy: "step"
stepsize: 200000
gamma: 0.1
max_iter: 800000
momentum: 0.9
weight_decay: 0.0001
snapshot: 2000
snapshot_prefix: "/data_1/2022/my_net_test_2022/snap/resnet_50"
solver_mode: GPU

resnet_50.prototxt

name: "ResNet-50"
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: false
    crop_size: 224
    #mean_value: 104.0
    #mean_value: 117.0
    #mean_value: 123.0
  }
  image_data_param {
    source: "/data_1/2022/train.txt"
    new_height: 224
    new_width: 224
    batch_size: 8
    shuffle: true
    }
}
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    crop_size: 224
    #mean_value: 104.0
    #mean_value: 117.0
    #mean_value: 123.0
  }
  image_data_param {
    source: "/data_1/2022/test.txt"
    batch_size: 8
    new_height: 224
    new_width: 224
    }
}
layer {
	bottom: "data"
	top: "conv1"
	name: "conv1"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 7
		pad: 3
		stride: 2
		weight_filler {
      		  type: "msra"
    		}
	}
}
...
...
...
...
...
layer {
	bottom: "pool5"
	top: "fc1000"
	name: "fc1000"
	type: "InnerProduct"
	inner_product_param {
		num_output: 5  ###你自己的类别数
		weight_filler {
      		  type: "msra"
    		}
    		bias_filler {
      		  type: "constant"
      		  value: 0
    	        }
	}
}

layer {
	bottom: "fc1000"
	bottom: "label"
	top: "prob"
	name: "prob"
	type: "SoftmaxWithLoss"
	include {
	  phase: TRAIN
	}
}
layer {
  bottom: "fc1000"
  bottom: "label"
  top: "accuracy@1"
  name: "accuracy/top1"
  type: "Accuracy"
  accuracy_param {
    top_k: 1
  }
}
layer {
  bottom: "fc1000"
  bottom: "label"
  top: "accuracy@5"
  name: "accuracy/top5"
  type: "Accuracy"
  accuracy_param {
    top_k: 5
  }
}

ResNet-50-deploy.prototxt

name: "ResNet-50"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224

layer {
	bottom: "data"
	top: "conv1"
	name: "conv1"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 7
		pad: 3
		stride: 2
	}
}
...
...
...

layer {
	bottom: "pool5"
	top: "fc1000"
	name: "fc1000"
	type: "InnerProduct"
	inner_product_param {
		num_output: 5 #自己的类别数量
	}
}

layer {
	bottom: "fc1000"
	top: "prob"
	name: "prob"
	type: "Softmax"
}

4.训练指令

./build/tools/caffe train --solver /data_1/2022/my_net_test_2022/my_resnet_50_solver.prototxt

接着训练指令：
./build/tools/caffe train --solver /data_1/2022/my_net_test_2022/my_resnet_50_solver.prototxt --weights /data_1/2022/my_net_test_2022/snap/resnet_50_iter_225000.caffemodel

一些打印如下：

I0119 11:46:54.103080  8442 net.cpp:202] label_data_1_split does not need backward computation.
I0119 11:46:54.103085  8442 net.cpp:202] data does not need backward computation.
I0119 11:46:54.103088  8442 net.cpp:244] This network produces output accuracy@1
I0119 11:46:54.103092  8442 net.cpp:244] This network produces output accuracy@5
I0119 11:46:54.103171  8442 net.cpp:257] Network initialization done.
I0119 11:46:54.103446  8442 solver.cpp:72] Finetuning from /data_1/2022/my_net_test_2022/snap/resnet_50_iter_225000.caffemodel
I0119 11:46:54.154101  8442 upgrade_proto.cpp:79] Attempting to upgrade batch norm layers using deprecated params: /data_1/2022/my_net_test_2022/snap/resnet_50_iter_225000.caffemodel
I0119 11:46:54.154167  8442 upgrade_proto.cpp:82] Successfully upgraded batch norm layers using deprecated params.
I0119 11:46:54.172962  8442 net.cpp:746] Ignoring source layer prob
I0119 11:46:54.175931  8442 solver.cpp:57] Solver scaffolding done.
I0119 11:46:54.183208  8442 caffe.cpp:239] Starting Optimization
I0119 11:46:54.183221  8442 solver.cpp:289] Solving ResNet-50
I0119 11:46:54.183226  8442 solver.cpp:290] Learning Rate Policy: step
I0119 11:46:54.187500  8442 solver.cpp:347] Iteration 0, Testing net (#0)
I0119 11:46:54.198930  8442 net.cpp:678] Ignoring source layer prob
I0119 11:46:54.561599  8442 blocking_queue.cpp:49] Waiting for data
I0119 11:48:21.886171  8442 blocking_queue.cpp:49] Waiting for data
I0119 11:49:52.645862  8442 blocking_queue.cpp:49] Waiting for data
I0119 11:50:32.406616  8442 solver.cpp:414]     Test net output #0: accuracy@1 = 0.98425
I0119 11:50:32.406733  8442 solver.cpp:414]     Test net output #1: accuracy@5 = 0.999833
I0119 11:50:32.574229  8442 solver.cpp:239] Iteration 0 (-2.31354e-41 iter/s, 218.385s/20 iters), loss = 0.014625
I0119 11:50:32.574259  8442 solver.cpp:258]     Train net output #0: accuracy@1 = 1
I0119 11:50:32.574265  8442 solver.cpp:258]     Train net output #1: accuracy@5 = 1
I0119 11:50:32.574271  8442 solver.cpp:258]     Train net output #2: prob = 0.014625 (* 1 = 0.014625 loss)
I0119 11:50:32.574281  8442 sgd_solver.cpp:112] Iteration 0, lr = 0.0005
I0119 11:50:35.615777  8442 solver.cpp:239] Iteration 20 (6.57589 iter/s, 3.04142s/20 iters), loss = 0.0107786
I0119 11:50:35.615824  8442 solver.cpp:258]     Train net output #0: accuracy@1 = 1
I0119 11:50:35.615831  8442 solver.cpp:258]     Train net output #1: accuracy@5 = 1
I0119 11:50:35.615839  8442 solver.cpp:258]     Train net output #2: prob = 0.0342208 (* 1 = 0.0342208 loss)
I0119 11:50:35.615845  8442 sgd_solver.cpp:112] Iteration 20, lr = 0.0005
I0119 11:50:38.667296  8442 solver.cpp:239] Iteration 40 (6.55443 iter/s, 3.05137s/20 iters), loss = 0.0113241
I0119 11:50:38.667331  8442 solver.cpp:258]     Train net output #0: accuracy@1 = 1
I0119 11:50:38.667340  8442 solver.cpp:258]     Train net output #1: accuracy@5 = 1
I0119 11:50:38.667351  8442 solver.cpp:258]     Train net output #2: prob = 0.00137874 (* 1 = 0.00137874 loss)
I0119 11:50:38.667358  8442 sgd_solver.cpp:112] Iteration 40, lr = 0.0005
I0119 11:50:41.711781  8442 solver.cpp:239] Iteration 60 (6.56963 iter/s, 3.04431s/20 iters), loss = 0.0104271
I0119 11:50:41.712178  8442 solver.cpp:258]     Train net output #0: accuracy@1 = 1
I0119 11:50:41.712193  8442 solver.cpp:258]     Train net output #1: accuracy@5 = 1
I0119 11:50:41.712205  8442 solver.cpp:258]     Train net output #2: prob = 0.00118907 (* 1 = 0.00118907 loss)
I0119 11:50:41.712213  8442 sgd_solver.cpp:112] Iteration 60, lr = 0.0005
I0119 11:50:44.749732  8442 solver.cpp:239] Iteration 80 (6.58447 iter/s, 3.03745s/20 iters), loss = 0.0108907

5.推理跑前向

训练完了会生成caffemodel模型文件，接着就可以用deploy文件和caffemodel文件来进行推理。

我是直接在caffe源码里面添加了一个cpp文件

.
├── caffe.cpp
├── caffe_test_c.cpp  ####新增！！！
├── CMakeLists.txt
├── compute_image_mean.cpp
├── convert_imageset.cpp
├── extra
├── extract_features.cpp
├── upgrade_net_proto_binary.cpp
├── upgrade_net_proto_text.cpp
└── upgrade_solver_proto_text.cpp

文件添加在这里，这里的cmakelist可以直接为每个cpp生成一个可执行文件。在build/tools目录下面：

caffe_test_c.cpp代码如下：

#include "boost/algorithm/string.hpp"
#include "caffe/caffe.hpp"
#include "caffe/util/signal_handler.h"
#include "opencv2/opencv.hpp"
#include <iostream>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>
#include <iostream>
#include <algorithm>
#include <string>
#include <vector>
#include <dirent.h>
#include <fstream>
#include <sys/types.h>
#include <sys/stat.h>
#include <sstream>
#include <iomanip>
#include <ctime>
#include <stdio.h>
using namespace std;
using namespace cv;

class Classifier {
public:
    Classifier(const std::string& model_file, const std::string& trained_file,
               const std::string& mean_file, const std::string& mean_value, const std::string& scale_value);
    std::vector<float> Predict(const cv::Mat& img);
    std::vector<vector<float> > PredictMulti(const cv::Mat& img);
    vector<float> extractFeatures(const cv::Mat &img, const std::string &blob_name);
private:
    void SetMean(const std::string& mean_file, const std::string& mean_value);
    void WrapInputLayer(std::vector<cv::Mat>* input_channels);
    void Preprocess(const cv::Mat& img, std::vector<cv::Mat>* input_channels);
private:
    boost::shared_ptr<caffe::Net<float> > net_;
    cv::Size input_geometry_;
    int num_channels_;
    bool use_mean_;
    cv::Mat mean_;
    float scale_;
    std::vector<std::string> labels_;
};
////////////////////////////////////////////////////////////////////////////////////////////////
using namespace caffe;
using caffe::Blob;
using caffe::Caffe;
using caffe::Net;
using caffe::Layer;
using caffe::Solver;
using caffe::shared_ptr;
using caffe::string;
using caffe::Timer;
using caffe::vector;
using std::ostringstream;


DEFINE_string(mean_file, "",
              "The mean file used to subtract from the input image.");
DEFINE_string(mean_value, "104,117,123",
              "If specified, can be one value or can be same as image channels"
              " - would subtract from the corresponding channel). Separated by ','."
              "Either mean_file or mean_value should be provided, not both.");

Classifier::Classifier(const string& model_file, const string& trained_file, const string& mean_file, const string& mean_value, const string& scale_value)
{
    Caffe::SetDevice(0);
    Caffe::set_mode(Caffe::GPU);
    net_.reset(new Net<float>(model_file, TEST));
    net_->CopyTrainedLayersFrom(trained_file);
    Blob<float>* input_layer = net_->input_blobs()[0];
    num_channels_ = input_layer->channels();
    CHECK(num_channels_ == 3 || num_channels_ == 1) << "Input layer should have 1 or 3 channels.";
    input_geometry_ = cv::Size(input_layer->width(), input_layer->height());
    if("" != mean_file || "" != mean_value)
    {
        use_mean_ = true;
        SetMean(mean_file, mean_value);
        scale_ = std::atof(scale_value.c_str());
    }
    else
    {
        use_mean_ = false;
        scale_ = 1;      // normailize scale value
    }
}

void Classifier::SetMean(const string& mean_file, const string& mean_value)
{
    if (!mean_file.empty()) {
        BlobProto blob_proto;
        ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);

        Blob<float> mean_blob;
        mean_blob.FromProto(blob_proto);
        CHECK_EQ(mean_blob.channels(), num_channels_)
            << "Number of channels of mean file doesn't match input layer.";

        std::vector<cv::Mat> channels;
        float* data = mean_blob.mutable_cpu_data();
        for (int i = 0; i < num_channels_; ++i) {
            cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);
            channels.push_back(channel);
            data += mean_blob.height() * mean_blob.width();
        }

        cv::Mat mean;
        cv::merge(channels, mean);

//        cv::Scalar channel_mean = cv::mean(mean);
//        mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
        mean_ = mean.clone();
    }
    if (!mean_value.empty()) {
        CHECK(mean_file.empty()) <<
                                 "Cannot specify mean_file and mean_value at the same time";
        stringstream ss(mean_value);
        vector<float> values;
        string item;
        while (getline(ss, item, ',')) {
            float value = std::atof(item.c_str());
            values.push_back(value);
        }
        CHECK((int)values.size() == 1 || (int)values.size() == num_channels_) <<
                                                                              "Specify either 1 mean_value or as many as channels: " << num_channels_;
        std::vector<cv::Mat> channels;
        for (int i = 0; i < num_channels_; ++i) {
            /* Extract an individual channel. */
            cv::Mat channel(input_geometry_.height, input_geometry_.width, CV_32FC1,
                            cv::Scalar(values[i]));
            channels.push_back(channel);
        }
        cv::merge(channels, mean_);
    }
}

void Classifier::Preprocess(const cv::Mat& img, std::vector<cv::Mat>* input_channels)
{
    cv::Mat sample;
    if (img.channels() == 3 && num_channels_ == 1)
        cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
    else if (img.channels() == 4 && num_channels_ == 1)
        cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
    else if (img.channels() == 4 && num_channels_ == 3)
        cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
    else if (img.channels() == 1 && num_channels_ == 3)
        cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);
    else
        sample = img;
    cv::Mat sample_resized;
    if (sample.size() != input_geometry_)
        cv::resize(sample, sample_resized, input_geometry_);
    else
        sample_resized = sample;
    cv::Mat sample_float;
    if (num_channels_ == 3)
        sample_resized.convertTo(sample_float, CV_32FC3);
    else
        sample_resized.convertTo(sample_float, CV_32FC1);
    cv::Mat sample_normalized;
    if(use_mean_)
    {
        cv::subtract(sample_float, mean_, sample_normalized);
        sample_normalized = sample_normalized*scale_;
    }
    else
        sample_normalized = sample_float.clone();
//    cv::Mat resimg=(sample_normalized-cv::Scalar(127.5, 127.5, 127.5))*0.0078125;
    cv::Mat resimg=sample_normalized;
    cv::split(resimg, *input_channels);
//    cv::split(sample_normalized, *input_channels);
    CHECK(reinterpret_cast<float*>(input_channels->at(0).data) == net_->input_blobs()[0]->cpu_data())
    << "Input channels are not wrapping the input layer of the network.";
}

vector<float> Classifier::extractFeatures(const cv::Mat &img, const std::string &blob_name) {
    vector<float> blob_features;
    Blob<float>* input_layer = net_->input_blobs()[0];
    input_layer->Reshape(1, num_channels_, input_geometry_.height, input_geometry_.width);
    net_->Reshape();
    std::vector<cv::Mat> input_channels;
    WrapInputLayer(&input_channels);
    Preprocess(img, &input_channels);
    net_->Forward();
    const boost::shared_ptr<Blob<float> > blob_layer = net_->blob_by_name(blob_name);
    const float* blob_layer_data = blob_layer->cpu_data();          // multi-dimension's data

    // TODO: the index's range
    int featureNum = blob_layer->count(1);

    for (int i = 0; i < featureNum; i++) {
        blob_features.push_back(*blob_layer_data);
        blob_layer_data++;
    }
    return blob_features;
}

vector<float> Classifier::Predict(const cv::Mat& img)
{
    Blob<float>* input_layer = net_->input_blobs()[0];
    input_layer->Reshape(1, num_channels_, input_geometry_.height, input_geometry_.width);
    net_->Reshape();
    std::vector<cv::Mat> input_channels;
    WrapInputLayer(&input_channels);
    Preprocess(img, &input_channels);
    net_->Forward();
    Blob<float>* output_layer = net_->output_blobs()[0];
    const float* begin = output_layer->cpu_data();
    const float* end = begin + output_layer->channels();
    return std::vector<float>(begin, end);
}

vector<vector<float> > Classifier::PredictMulti(const cv::Mat& img)
{
    Blob<float>* input_layer = net_->input_blobs()[0];
    input_layer->Reshape(1, num_channels_, input_geometry_.height, input_geometry_.width);
    net_->Reshape();
    std::vector<cv::Mat> input_channels;
    WrapInputLayer(&input_channels);
    Preprocess(img, &input_channels);
    net_->Forward();
    Blob<float>* output_layer1 = net_->output_blobs()[0];
    Blob<float>* output_layer2 = net_->output_blobs()[1];
    const float* begin1 = output_layer1->cpu_data();
    const float* end1 = begin1 + output_layer1->channels();
    std::vector<float> vec1 = std::vector<float>(begin1, end1);
    const float* begin2 = output_layer2->cpu_data();
    const float* end2 = begin2 + output_layer2->channels();
    std::vector<float> vec2 = std::vector<float>(begin2, end2);
    std::vector<vector<float> > res;
    res.push_back(vec1);
    res.push_back(vec2);
    return res;
}

void Classifier::WrapInputLayer(std::vector<cv::Mat>* input_channels)
{
    Blob<float>* input_layer = net_->input_blobs()[0];

    int width = input_layer->width();
    int height = input_layer->height();
    float* input_data = input_layer->mutable_cpu_data();
    for (int i = 0; i < input_layer->channels(); ++i) {
        cv::Mat channel(height, width, CV_32FC1, input_data);
        input_channels->push_back(channel);
        input_data += width * height;
    }
}
////////////////////////////////////////////////////////////////////////////////////////////////
struct Info
{
    int idx;
    float score;
};

bool sort_score(Info& i1, Info& i2)
{
    return i1.score > i2.score;
}

int main()
{
    string cls_model = "/data_1/2022/my_net_test_2022/ResNet-50-deploy.prototxt";
    string cls_weights = "/data_1/2022/my_net_test_2022/snap/resnet_50_iter_225000.caffemodel";

    Classifier* cls= new Classifier(cls_model, cls_weights, "", "","");

    vector<string> v_files_all;
    vector<string> v_files_test;

    ifstream infile("/data_1/2022/test_list.txt");
    string line;
    while(infile >> line)
    {
        cv::Mat img = cv::imread(line);
        if(img.empty())continue;
        Mat dst = img.clone();
        vector<float> predictions = cls->Predict(dst);
        vector<Info> infos;
        for(int k = 0; k <predictions.size(); k++)
        {
            Info info;
            info.idx = k;
            info.score = predictions[k];
            infos.push_back(info);
        }
        sort(infos.begin(), infos.end(), sort_score);

        Info info = infos[0];
        int idx = info.idx;

        std::cout<<"path="<<line<<std::endl;
        std::cout<<"label="<<idx<<std::endl;
        cv::imshow("img",img);
        cv::waitKey(0);
    }
    return 0;
}

6.三个完整网络文件

my_resnet_50_solver.prototxt

net: "/data_1/2022/my_net_test_2022/my_resnet_50.prototxt"
test_iter: 3000
test_interval: 3000
#test_initialization: true
display: 20
average_loss: 1000
base_lr: 0.0005
lr_policy: "step"
stepsize: 200000
gamma: 0.1
max_iter: 800000
momentum: 0.9
weight_decay: 0.0001
snapshot: 2000
snapshot_prefix: "/data_1/2022/my_net_test_2022/snap/resnet_50"
solver_mode: GPU

my_resnet_50.prototxt

name: "ResNet-50"
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: false
    crop_size: 224
    #mean_value: 104.0
    #mean_value: 117.0
    #mean_value: 123.0
  }
  image_data_param {
    source: "/data_1/2022/train-20211025.txt"
    new_height: 224
    new_width: 224
    batch_size: 8
    shuffle: true
    }
}
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    crop_size: 224
    #mean_value: 104.0
    #mean_value: 117.0
    #mean_value: 123.0
  }
  image_data_param {
    source: "/data_1/2022/val-20211025.txt"
    batch_size: 8
    new_height: 224
    new_width: 224
    }
}
layer {
	bottom: "data"
	top: "conv1"
	name: "conv1"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 7
		pad: 3
		stride: 2
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "conv1"
	top: "conv1"
	name: "bn_conv1"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "conv1"
	top: "conv1"
	name: "scale_conv1"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "conv1"
	top: "conv1"
	name: "conv1_relu"
	type: "ReLU"
}

layer {
	bottom: "conv1"
	top: "pool1"
	name: "pool1"
	type: "Pooling"
	pooling_param {
		kernel_size: 3
		stride: 2
		pool: MAX
	}
}

layer {
	bottom: "pool1"
	top: "res2a_branch1"
	name: "res2a_branch1"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2a_branch1"
	top: "res2a_branch1"
	name: "bn2a_branch1"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2a_branch1"
	top: "res2a_branch1"
	name: "scale2a_branch1"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "pool1"
	top: "res2a_branch2a"
	name: "res2a_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2a_branch2a"
	top: "res2a_branch2a"
	name: "bn2a_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2a_branch2a"
	top: "res2a_branch2a"
	name: "scale2a_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2a_branch2a"
	top: "res2a_branch2a"
	name: "res2a_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res2a_branch2a"
	top: "res2a_branch2b"
	name: "res2a_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2a_branch2b"
	top: "res2a_branch2b"
	name: "bn2a_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2a_branch2b"
	top: "res2a_branch2b"
	name: "scale2a_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2a_branch2b"
	top: "res2a_branch2b"
	name: "res2a_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res2a_branch2b"
	top: "res2a_branch2c"
	name: "res2a_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2a_branch2c"
	top: "res2a_branch2c"
	name: "bn2a_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2a_branch2c"
	top: "res2a_branch2c"
	name: "scale2a_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2a_branch1"
	bottom: "res2a_branch2c"
	top: "res2a"
	name: "res2a"
	type: "Eltwise"
}

layer {
	bottom: "res2a"
	top: "res2a"
	name: "res2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res2a"
	top: "res2b_branch2a"
	name: "res2b_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2b_branch2a"
	top: "res2b_branch2a"
	name: "bn2b_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2b_branch2a"
	top: "res2b_branch2a"
	name: "scale2b_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2b_branch2a"
	top: "res2b_branch2a"
	name: "res2b_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res2b_branch2a"
	top: "res2b_branch2b"
	name: "res2b_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2b_branch2b"
	top: "res2b_branch2b"
	name: "bn2b_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2b_branch2b"
	top: "res2b_branch2b"
	name: "scale2b_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2b_branch2b"
	top: "res2b_branch2b"
	name: "res2b_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res2b_branch2b"
	top: "res2b_branch2c"
	name: "res2b_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2b_branch2c"
	top: "res2b_branch2c"
	name: "bn2b_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2b_branch2c"
	top: "res2b_branch2c"
	name: "scale2b_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2a"
	bottom: "res2b_branch2c"
	top: "res2b"
	name: "res2b"
	type: "Eltwise"
}

layer {
	bottom: "res2b"
	top: "res2b"
	name: "res2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res2b"
	top: "res2c_branch2a"
	name: "res2c_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2c_branch2a"
	top: "res2c_branch2a"
	name: "bn2c_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2c_branch2a"
	top: "res2c_branch2a"
	name: "scale2c_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2c_branch2a"
	top: "res2c_branch2a"
	name: "res2c_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res2c_branch2a"
	top: "res2c_branch2b"
	name: "res2c_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 64
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2c_branch2b"
	top: "res2c_branch2b"
	name: "bn2c_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2c_branch2b"
	top: "res2c_branch2b"
	name: "scale2c_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2c_branch2b"
	top: "res2c_branch2b"
	name: "res2c_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res2c_branch2b"
	top: "res2c_branch2c"
	name: "res2c_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res2c_branch2c"
	top: "res2c_branch2c"
	name: "bn2c_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res2c_branch2c"
	top: "res2c_branch2c"
	name: "scale2c_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2b"
	bottom: "res2c_branch2c"
	top: "res2c"
	name: "res2c"
	type: "Eltwise"
}

layer {
	bottom: "res2c"
	top: "res2c"
	name: "res2c_relu"
	type: "ReLU"
}

layer {
	bottom: "res2c"
	top: "res3a_branch1"
	name: "res3a_branch1"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3a_branch1"
	top: "res3a_branch1"
	name: "bn3a_branch1"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3a_branch1"
	top: "res3a_branch1"
	name: "scale3a_branch1"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res2c"
	top: "res3a_branch2a"
	name: "res3a_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3a_branch2a"
	top: "res3a_branch2a"
	name: "bn3a_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3a_branch2a"
	top: "res3a_branch2a"
	name: "scale3a_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3a_branch2a"
	top: "res3a_branch2a"
	name: "res3a_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res3a_branch2a"
	top: "res3a_branch2b"
	name: "res3a_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3a_branch2b"
	top: "res3a_branch2b"
	name: "bn3a_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3a_branch2b"
	top: "res3a_branch2b"
	name: "scale3a_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3a_branch2b"
	top: "res3a_branch2b"
	name: "res3a_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res3a_branch2b"
	top: "res3a_branch2c"
	name: "res3a_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3a_branch2c"
	top: "res3a_branch2c"
	name: "bn3a_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3a_branch2c"
	top: "res3a_branch2c"
	name: "scale3a_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3a_branch1"
	bottom: "res3a_branch2c"
	top: "res3a"
	name: "res3a"
	type: "Eltwise"
}

layer {
	bottom: "res3a"
	top: "res3a"
	name: "res3a_relu"
	type: "ReLU"
}

layer {
	bottom: "res3a"
	top: "res3b_branch2a"
	name: "res3b_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3b_branch2a"
	top: "res3b_branch2a"
	name: "bn3b_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3b_branch2a"
	top: "res3b_branch2a"
	name: "scale3b_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3b_branch2a"
	top: "res3b_branch2a"
	name: "res3b_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res3b_branch2a"
	top: "res3b_branch2b"
	name: "res3b_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3b_branch2b"
	top: "res3b_branch2b"
	name: "bn3b_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3b_branch2b"
	top: "res3b_branch2b"
	name: "scale3b_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3b_branch2b"
	top: "res3b_branch2b"
	name: "res3b_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res3b_branch2b"
	top: "res3b_branch2c"
	name: "res3b_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3b_branch2c"
	top: "res3b_branch2c"
	name: "bn3b_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3b_branch2c"
	top: "res3b_branch2c"
	name: "scale3b_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3a"
	bottom: "res3b_branch2c"
	top: "res3b"
	name: "res3b"
	type: "Eltwise"
}

layer {
	bottom: "res3b"
	top: "res3b"
	name: "res3b_relu"
	type: "ReLU"
}

layer {
	bottom: "res3b"
	top: "res3c_branch2a"
	name: "res3c_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3c_branch2a"
	top: "res3c_branch2a"
	name: "bn3c_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3c_branch2a"
	top: "res3c_branch2a"
	name: "scale3c_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3c_branch2a"
	top: "res3c_branch2a"
	name: "res3c_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res3c_branch2a"
	top: "res3c_branch2b"
	name: "res3c_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3c_branch2b"
	top: "res3c_branch2b"
	name: "bn3c_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3c_branch2b"
	top: "res3c_branch2b"
	name: "scale3c_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3c_branch2b"
	top: "res3c_branch2b"
	name: "res3c_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res3c_branch2b"
	top: "res3c_branch2c"
	name: "res3c_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3c_branch2c"
	top: "res3c_branch2c"
	name: "bn3c_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3c_branch2c"
	top: "res3c_branch2c"
	name: "scale3c_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3b"
	bottom: "res3c_branch2c"
	top: "res3c"
	name: "res3c"
	type: "Eltwise"
}

layer {
	bottom: "res3c"
	top: "res3c"
	name: "res3c_relu"
	type: "ReLU"
}

layer {
	bottom: "res3c"
	top: "res3d_branch2a"
	name: "res3d_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3d_branch2a"
	top: "res3d_branch2a"
	name: "bn3d_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3d_branch2a"
	top: "res3d_branch2a"
	name: "scale3d_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3d_branch2a"
	top: "res3d_branch2a"
	name: "res3d_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res3d_branch2a"
	top: "res3d_branch2b"
	name: "res3d_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 128
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3d_branch2b"
	top: "res3d_branch2b"
	name: "bn3d_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3d_branch2b"
	top: "res3d_branch2b"
	name: "scale3d_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3d_branch2b"
	top: "res3d_branch2b"
	name: "res3d_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res3d_branch2b"
	top: "res3d_branch2c"
	name: "res3d_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res3d_branch2c"
	top: "res3d_branch2c"
	name: "bn3d_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res3d_branch2c"
	top: "res3d_branch2c"
	name: "scale3d_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3c"
	bottom: "res3d_branch2c"
	top: "res3d"
	name: "res3d"
	type: "Eltwise"
}

layer {
	bottom: "res3d"
	top: "res3d"
	name: "res3d_relu"
	type: "ReLU"
}

layer {
	bottom: "res3d"
	top: "res4a_branch1"
	name: "res4a_branch1"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4a_branch1"
	top: "res4a_branch1"
	name: "bn4a_branch1"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4a_branch1"
	top: "res4a_branch1"
	name: "scale4a_branch1"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res3d"
	top: "res4a_branch2a"
	name: "res4a_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4a_branch2a"
	top: "res4a_branch2a"
	name: "bn4a_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4a_branch2a"
	top: "res4a_branch2a"
	name: "scale4a_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4a_branch2a"
	top: "res4a_branch2a"
	name: "res4a_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4a_branch2a"
	top: "res4a_branch2b"
	name: "res4a_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4a_branch2b"
	top: "res4a_branch2b"
	name: "bn4a_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4a_branch2b"
	top: "res4a_branch2b"
	name: "scale4a_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4a_branch2b"
	top: "res4a_branch2b"
	name: "res4a_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4a_branch2b"
	top: "res4a_branch2c"
	name: "res4a_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4a_branch2c"
	top: "res4a_branch2c"
	name: "bn4a_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4a_branch2c"
	top: "res4a_branch2c"
	name: "scale4a_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4a_branch1"
	bottom: "res4a_branch2c"
	top: "res4a"
	name: "res4a"
	type: "Eltwise"
}

layer {
	bottom: "res4a"
	top: "res4a"
	name: "res4a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4a"
	top: "res4b_branch2a"
	name: "res4b_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4b_branch2a"
	top: "res4b_branch2a"
	name: "bn4b_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4b_branch2a"
	top: "res4b_branch2a"
	name: "scale4b_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4b_branch2a"
	top: "res4b_branch2a"
	name: "res4b_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4b_branch2a"
	top: "res4b_branch2b"
	name: "res4b_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4b_branch2b"
	top: "res4b_branch2b"
	name: "bn4b_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4b_branch2b"
	top: "res4b_branch2b"
	name: "scale4b_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4b_branch2b"
	top: "res4b_branch2b"
	name: "res4b_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4b_branch2b"
	top: "res4b_branch2c"
	name: "res4b_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4b_branch2c"
	top: "res4b_branch2c"
	name: "bn4b_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4b_branch2c"
	top: "res4b_branch2c"
	name: "scale4b_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4a"
	bottom: "res4b_branch2c"
	top: "res4b"
	name: "res4b"
	type: "Eltwise"
}

layer {
	bottom: "res4b"
	top: "res4b"
	name: "res4b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4b"
	top: "res4c_branch2a"
	name: "res4c_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4c_branch2a"
	top: "res4c_branch2a"
	name: "bn4c_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4c_branch2a"
	top: "res4c_branch2a"
	name: "scale4c_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4c_branch2a"
	top: "res4c_branch2a"
	name: "res4c_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4c_branch2a"
	top: "res4c_branch2b"
	name: "res4c_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4c_branch2b"
	top: "res4c_branch2b"
	name: "bn4c_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4c_branch2b"
	top: "res4c_branch2b"
	name: "scale4c_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4c_branch2b"
	top: "res4c_branch2b"
	name: "res4c_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4c_branch2b"
	top: "res4c_branch2c"
	name: "res4c_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4c_branch2c"
	top: "res4c_branch2c"
	name: "bn4c_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4c_branch2c"
	top: "res4c_branch2c"
	name: "scale4c_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4b"
	bottom: "res4c_branch2c"
	top: "res4c"
	name: "res4c"
	type: "Eltwise"
}

layer {
	bottom: "res4c"
	top: "res4c"
	name: "res4c_relu"
	type: "ReLU"
}

layer {
	bottom: "res4c"
	top: "res4d_branch2a"
	name: "res4d_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4d_branch2a"
	top: "res4d_branch2a"
	name: "bn4d_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4d_branch2a"
	top: "res4d_branch2a"
	name: "scale4d_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4d_branch2a"
	top: "res4d_branch2a"
	name: "res4d_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4d_branch2a"
	top: "res4d_branch2b"
	name: "res4d_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4d_branch2b"
	top: "res4d_branch2b"
	name: "bn4d_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4d_branch2b"
	top: "res4d_branch2b"
	name: "scale4d_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4d_branch2b"
	top: "res4d_branch2b"
	name: "res4d_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4d_branch2b"
	top: "res4d_branch2c"
	name: "res4d_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4d_branch2c"
	top: "res4d_branch2c"
	name: "bn4d_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4d_branch2c"
	top: "res4d_branch2c"
	name: "scale4d_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4c"
	bottom: "res4d_branch2c"
	top: "res4d"
	name: "res4d"
	type: "Eltwise"
}

layer {
	bottom: "res4d"
	top: "res4d"
	name: "res4d_relu"
	type: "ReLU"
}

layer {
	bottom: "res4d"
	top: "res4e_branch2a"
	name: "res4e_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4e_branch2a"
	top: "res4e_branch2a"
	name: "bn4e_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4e_branch2a"
	top: "res4e_branch2a"
	name: "scale4e_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4e_branch2a"
	top: "res4e_branch2a"
	name: "res4e_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4e_branch2a"
	top: "res4e_branch2b"
	name: "res4e_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4e_branch2b"
	top: "res4e_branch2b"
	name: "bn4e_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4e_branch2b"
	top: "res4e_branch2b"
	name: "scale4e_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4e_branch2b"
	top: "res4e_branch2b"
	name: "res4e_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4e_branch2b"
	top: "res4e_branch2c"
	name: "res4e_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4e_branch2c"
	top: "res4e_branch2c"
	name: "bn4e_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4e_branch2c"
	top: "res4e_branch2c"
	name: "scale4e_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4d"
	bottom: "res4e_branch2c"
	top: "res4e"
	name: "res4e"
	type: "Eltwise"
}

layer {
	bottom: "res4e"
	top: "res4e"
	name: "res4e_relu"
	type: "ReLU"
}

layer {
	bottom: "res4e"
	top: "res4f_branch2a"
	name: "res4f_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4f_branch2a"
	top: "res4f_branch2a"
	name: "bn4f_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4f_branch2a"
	top: "res4f_branch2a"
	name: "scale4f_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4f_branch2a"
	top: "res4f_branch2a"
	name: "res4f_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res4f_branch2a"
	top: "res4f_branch2b"
	name: "res4f_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 256
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4f_branch2b"
	top: "res4f_branch2b"
	name: "bn4f_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4f_branch2b"
	top: "res4f_branch2b"
	name: "scale4f_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4f_branch2b"
	top: "res4f_branch2b"
	name: "res4f_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res4f_branch2b"
	top: "res4f_branch2c"
	name: "res4f_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 1024
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res4f_branch2c"
	top: "res4f_branch2c"
	name: "bn4f_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res4f_branch2c"
	top: "res4f_branch2c"
	name: "scale4f_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4e"
	bottom: "res4f_branch2c"
	top: "res4f"
	name: "res4f"
	type: "Eltwise"
}

layer {
	bottom: "res4f"
	top: "res4f"
	name: "res4f_relu"
	type: "ReLU"
}

layer {
	bottom: "res4f"
	top: "res5a_branch1"
	name: "res5a_branch1"
	type: "Convolution"
	convolution_param {
		num_output: 2048
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5a_branch1"
	top: "res5a_branch1"
	name: "bn5a_branch1"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5a_branch1"
	top: "res5a_branch1"
	name: "scale5a_branch1"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res4f"
	top: "res5a_branch2a"
	name: "res5a_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 2
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5a_branch2a"
	top: "res5a_branch2a"
	name: "bn5a_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5a_branch2a"
	top: "res5a_branch2a"
	name: "scale5a_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5a_branch2a"
	top: "res5a_branch2a"
	name: "res5a_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res5a_branch2a"
	top: "res5a_branch2b"
	name: "res5a_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5a_branch2b"
	top: "res5a_branch2b"
	name: "bn5a_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5a_branch2b"
	top: "res5a_branch2b"
	name: "scale5a_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5a_branch2b"
	top: "res5a_branch2b"
	name: "res5a_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res5a_branch2b"
	top: "res5a_branch2c"
	name: "res5a_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 2048
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5a_branch2c"
	top: "res5a_branch2c"
	name: "bn5a_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5a_branch2c"
	top: "res5a_branch2c"
	name: "scale5a_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5a_branch1"
	bottom: "res5a_branch2c"
	top: "res5a"
	name: "res5a"
	type: "Eltwise"
}

layer {
	bottom: "res5a"
	top: "res5a"
	name: "res5a_relu"
	type: "ReLU"
}

layer {
	bottom: "res5a"
	top: "res5b_branch2a"
	name: "res5b_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5b_branch2a"
	top: "res5b_branch2a"
	name: "bn5b_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5b_branch2a"
	top: "res5b_branch2a"
	name: "scale5b_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5b_branch2a"
	top: "res5b_branch2a"
	name: "res5b_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res5b_branch2a"
	top: "res5b_branch2b"
	name: "res5b_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5b_branch2b"
	top: "res5b_branch2b"
	name: "bn5b_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5b_branch2b"
	top: "res5b_branch2b"
	name: "scale5b_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5b_branch2b"
	top: "res5b_branch2b"
	name: "res5b_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res5b_branch2b"
	top: "res5b_branch2c"
	name: "res5b_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 2048
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5b_branch2c"
	top: "res5b_branch2c"
	name: "bn5b_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5b_branch2c"
	top: "res5b_branch2c"
	name: "scale5b_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5a"
	bottom: "res5b_branch2c"
	top: "res5b"
	name: "res5b"
	type: "Eltwise"
}

layer {
	bottom: "res5b"
	top: "res5b"
	name: "res5b_relu"
	type: "ReLU"
}

layer {
	bottom: "res5b"
	top: "res5c_branch2a"
	name: "res5c_branch2a"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5c_branch2a"
	top: "res5c_branch2a"
	name: "bn5c_branch2a"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5c_branch2a"
	top: "res5c_branch2a"
	name: "scale5c_branch2a"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5c_branch2a"
	top: "res5c_branch2a"
	name: "res5c_branch2a_relu"
	type: "ReLU"
}

layer {
	bottom: "res5c_branch2a"
	top: "res5c_branch2b"
	name: "res5c_branch2b"
	type: "Convolution"
	convolution_param {
		num_output: 512
		kernel_size: 3
		pad: 1
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5c_branch2b"
	top: "res5c_branch2b"
	name: "bn5c_branch2b"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5c_branch2b"
	top: "res5c_branch2b"
	name: "scale5c_branch2b"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5c_branch2b"
	top: "res5c_branch2b"
	name: "res5c_branch2b_relu"
	type: "ReLU"
}

layer {
	bottom: "res5c_branch2b"
	top: "res5c_branch2c"
	name: "res5c_branch2c"
	type: "Convolution"
	convolution_param {
		num_output: 2048
		kernel_size: 1
		pad: 0
		stride: 1
		bias_term: false
		weight_filler {
      		  type: "msra"
    		}
	}
}

layer {
	bottom: "res5c_branch2c"
	top: "res5c_branch2c"
	name: "bn5c_branch2c"
	type: "BatchNorm"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}

layer {
	bottom: "res5c_branch2c"
	top: "res5c_branch2c"
	name: "scale5c_branch2c"
	type: "Scale"
	scale_param {
		bias_term: true
	}
}

layer {
	bottom: "res5b"
	bottom: "res5c_branch2c"
	top: "res5c"
	name: "res5c"
	type: "Eltwise"
}

layer {
	bottom: "res5c"
	top: "res5c"
	name: "res5c_relu"
	type: "ReLU"
}

layer {
	bottom: "res5c"
	top: "pool5"
	name: "pool5"
	type: "Pooling"
	pooling_param {
		kernel_size: 7
		stride: 1
		pool: AVE
	}
}

layer {
	bottom: "pool5"
	top: "fc1000"
	name: "fc1000"
	type: "InnerProduct"
	inner_product_param {
		num_output: 5
		weight_filler {
      		  type: "msra"
    		}
    		bias_filler {
      		  type: "constant"
      		  value: 0
    	        }
	}
}

layer {
	bottom: "fc1000"
	bottom: "label"
	top: "prob"
	name: "prob"
	type: "SoftmaxWithLoss"
	include {
	  phase: TRAIN
	}
}
layer {
  bottom: "fc1000"
  bottom: "label"
  top: "accuracy@1"
  name: "accuracy/top1"
  type: "Accuracy"
  accuracy_param {
    top_k: 1
  }
}
layer {
  bottom: "fc1000"
  bottom: "label"
  top: "accuracy@5"
  name: "accuracy/top5"
  type: "Accuracy"
  accuracy_param {
    top_k: 5
  }
}