caffe提取每一层中的特征，在matlab或python查看

参考博客：

http://blog.csdn.net/abc8730866/article/details/52522843

http://blog.csdn.net/lijiancheng0614/article/details/48180331

编译出extract_features.exe模块

在×64、Release模式下编译生成extract_features.exe

将某一层的特征向量生成lmdb文件

在caffe工程的examples下新建一个文件夹，命名为_temp

将examples\images下的图片写成一个文本文档，命名为file_list.txt，放在_temp文件夹下

将examples/eature_extraction/imagenet_val.prototxt复制到之前新建的_temp文件夹。

打开imagenet_val.prototxt，修改以下file_list.txt的路径，对应准确即可：

在models\bvlc_reference_caffenet目录中，下载bvlc_reference_caffenet.caffemodel文件

在caffe根目录下，新建bat脚本，

Build\x64\Release\extract_features.exe models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel examples/_temp/imagenet_val.prototxt fc7 examples/_temp/features 10 lmdb
pause

可以在examples/_temp/features中生成提取的lmdb文件

将lmdb文件转化为mat文件

feat_helper_pb2.py

# Generated by the protocol buffer compiler.  DO NOT EDIT!

from google.protobuf import descriptor
from google.protobuf import message
from google.protobuf import reflection
from google.protobuf import descriptor_pb2

# @@protoc_insertion_point(imports)

DESCRIPTOR = descriptor.FileDescriptor(
  name='datum.proto',
  package='feat_extract',
  serialized_pb='\n\x0b\x64\x61tum.proto\x12\x0c\x66\x65\x61t_extract\"i\n\x05\x44\x61tum\x12\x10\n\x08\x63hannels\x18\x01 \x01(\x05\x12\x0e\n\x06height\x18\x02 \x01(\x05\x12\r\n\x05width\x18\x03 \x01(\x05\x12\x0c\n\x04\x64\x61ta\x18\x04 \x01(\x0c\x12\r\n\x05label\x18\x05 \x01(\x05\x12\x12\n\nfloat_data\x18\x06 \x03(\x02')

_DATUM = descriptor.Descriptor(
  name='Datum',
  full_name='feat_extract.Datum',
  filename=None,
  file=DESCRIPTOR,
  containing_type=None,
  fields=[
    descriptor.FieldDescriptor(
      name='channels', full_name='feat_extract.Datum.channels', index=0,
      number=1, type=5, cpp_type=1, label=1,
      has_default_value=False, default_value=0,
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
    descriptor.FieldDescriptor(
      name='height', full_name='feat_extract.Datum.height', index=1,
      number=2, type=5, cpp_type=1, label=1,
      has_default_value=False, default_value=0,
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
    descriptor.FieldDescriptor(
      name='width', full_name='feat_extract.Datum.width', index=2,
      number=3, type=5, cpp_type=1, label=1,
      has_default_value=False, default_value=0,
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
    descriptor.FieldDescriptor(
      name='data', full_name='feat_extract.Datum.data', index=3,
      number=4, type=12, cpp_type=9, label=1,
      has_default_value=False, default_value="",
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
    descriptor.FieldDescriptor(
      name='label', full_name='feat_extract.Datum.label', index=4,
      number=5, type=5, cpp_type=1, label=1,
      has_default_value=False, default_value=0,
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
    descriptor.FieldDescriptor(
      name='float_data', full_name='feat_extract.Datum.float_data', index=5,
      number=6, type=2, cpp_type=6, label=3,
      has_default_value=False, default_value=[],
      message_type=None, enum_type=None, containing_type=None,
      is_extension=False, extension_scope=None,
      options=None),
  ],
  extensions=[
  ],
  nested_types=[],
  enum_types=[
  ],
  options=None,
  is_extendable=False,
  extension_ranges=[],
  serialized_start=29,
  serialized_end=134,
)

DESCRIPTOR.message_types_by_name['Datum'] = _DATUM

class Datum(message.Message):
  __metaclass__ = reflection.GeneratedProtocolMessageType
  DESCRIPTOR = _DATUM

  # @@protoc_insertion_point(class_scope:feat_extract.Datum)

# @@protoc_insertion_point(module_scope)

lmdb2mat.py

import lmdb
import feat_helper_pb2
import numpy as np
import scipy.io as sio
import time

def main(argv):
    lmdb_name = sys.argv[1]
    print "%s" % sys.argv[1]
    batch_num = int(sys.argv[2]);
    batch_size = int(sys.argv[3]);
    window_num = batch_num*batch_size;

    start = time.time()
    if 'db' not in locals().keys():
        db = lmdb.open(lmdb_name)
        txn= db.begin()
        cursor = txn.cursor()
        cursor.iternext()
        datum = feat_helper_pb2.Datum()

        keys = []
        values = []
        for key, value in enumerate( cursor.iternext_nodup()):
            keys.append(key)
            values.append(cursor.value())

    ft = np.zeros((window_num, int(sys.argv[4])))
    for im_idx in range(window_num):
        datum.ParseFromString(values[im_idx])
        ft[im_idx, :] = datum.float_data

    print 'time 1: %f' %(time.time() - start)
    sio.savemat(sys.argv[5], {'feats':ft})
    print 'time 2: %f' %(time.time() - start)
    print 'done!'

if __name__ == '__main__':
    import sys
    main(sys.argv)

将这个两个文件放在_temp文件夹中（位置可随意放置），cmd打开python，进入到该目录，

python lmdb2mat.py features 1 10 4096 features_fc7.mat

在ubantu下命令的格式的参考，

LMDB=./examples/_temp/features_fc7 # lmdb文件路径
BATCHNUM=1
BATCHSIZE=10

# DIM=290400 # feature长度，conv1

# DIM=43264 # conv5

DIM=4096
OUT=./examples/_temp/features_fc7.mat #mat文件保存路径
python ./lmdb2mat.py $LMDB $BATCHNUM $BATCHSIZE $DIM $OUT

可生成一个mat文件，

新建matlab函数及脚本，对该mat文件进行可视化

display_network.m

function [h, array] = display_network(A, opt_normalize, opt_graycolor, cols, opt_colmajor)
% This function visualizes filters in matrix A. Each column of A is a
% filter. We will reshape each column into a square image and visualizes
% on each cell of the visualization panel.
% All other parameters are optional, usually you do not need to worry
% about it.
% opt_normalize: whether we need to normalize the filter so that all of
% them can have similar contrast. Default value is true.
% opt_graycolor: whether we use gray as the heat map. Default is true.
% cols: how many columns are there in the display. Default value is the
% squareroot of the number of columns in A.
% opt_colmajor: you can switch convention to row major for A. In that
% case, each row of A is a filter. Default value is false.
warning off all

if ~exist('opt_normalize', 'var') || isempty(opt_normalize)
    opt_normalize= true;
end

if ~exist('opt_graycolor', 'var') || isempty(opt_graycolor)
    opt_graycolor= true;
end

if ~exist('opt_colmajor', 'var') || isempty(opt_colmajor)
    opt_colmajor = false;
end

% rescale
A = A - mean(A(:));

if opt_graycolor, colormap(gray); end

% compute rows, cols
[L M]=size(A);
sz=sqrt(L);
buf=;
if ~exist('cols', 'var')
    if floor(sqrt(M))^ ~= M
        n=ceil(sqrt(M));
        while mod(M, n)~= && n<1.2*sqrt(M), n=n+; end
        m=ceil(M/n);
    else
        n=sqrt(M);
        m=n;
    end
else
    n = cols;
    m = ceil(M/n);
end

array=-ones(buf+m*(sz+buf),buf+n*(sz+buf));

if ~opt_graycolor
    array = 0.1.* array;
end

if ~opt_colmajor
    k=;
    for i=:m
        for j=:n
            if k>M,
                continue;
            end
            clim=max(abs(A(:,k)));
            if opt_normalize
                array(buf+(i-)*(sz+buf)+(:sz),buf+(j-)*(sz+buf)+(:sz))=reshape(A(:,k),sz,sz)'/clim;
            else
                array(buf+(i-)*(sz+buf)+(:sz),buf+(j-)*(sz+buf)+(:sz))=reshape(A(:,k),sz,sz)'/max(abs(A(:)));
            end
            k=k+;
        end
    end
else
    k=;
    for j=:n
        for i=:m
            if k>M,
                continue;
            end
            clim=max(abs(A(:,k)));
            if opt_normalize
                array(buf+(i-)*(sz+buf)+(:sz),buf+(j-)*(sz+buf)+(:sz))=reshape(A(:,k),sz,sz)'/clim;
            else
                array(buf+(i-)*(sz+buf)+(:sz),buf+(j-)*(sz+buf)+(:sz))=reshape(A(:,k),sz,sz)';
            end
            k=k+;
        end
    end
end

if opt_graycolor
    h=imagesc(array);
else
    h=imagesc(array,'EraseMode','none',[- ]);
end
axis image off

drawnow;

warning on all

在该目录下，新建脚本，调用该函数

nsample = ;
% num_output = ; % conv1
% num_output = ; % conv5
num_output = ; % fc7

load features_fc7.mat
width = size(feats, );
nmap = width / num_output;

for i =  : nsample
    feat = feats(i, :);
    feat = reshape(feat, [nmap num_output]);
    figure('name', sprintf('image #%d', i));
    display_network(feat);
end

在python中读取该mat文件

import scipy.io
matfile = 'features_fc7.mat'
data = scipy.io.loadmat(matfile)