caffe下用AlexNet模型提取图像特征并从指定层输出特征向量

最新推荐文章于 2023-03-28 13:26:53 发布

HitagiDesu

最新推荐文章于 2023-03-28 13:26:53 发布

阅读量3.8k

点赞数 2

本文链接：https://blog.csdn.net/zhansama/article/details/80658880

版权

caffe自带的工具extract_features.bin可用于提取输入图像的特征并选择fc层进行输出

选择需要提取特征的图像，并将其路径导入txt

./example/_temp


# 建立临时目录

mkdir examples/_temp

# 生成图像路径列表文件

find `pwd`/examples/images -type f -exec echo {} \; > examples/_temp/temp.txt

# 每个图像路径最后都有一个分类标签，因此在每条路径最后加上0代表结束

sed "s/$/ 0/" examples/_temp/temp.txt > examples/_temp/file_list.txt

下载bvlc_reference_caffenet.caffemodel，并制作网络结构文件

./models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
./examples/_temp/imagenet_val.prototxt
```
./data/ilsvrc12/get_ilsvrc_aux.sh

# 导入网络结构文件

cp examples/feature_extraction/imagenet_val.prototxt examples/_temp
```
使用extract_features.bin提取特征，并以lmdb格式保存。运行参数为extract_features.bin $MODEL $PROTOTXT $LAYER $LMDB_OUTPUT_PATH $BATCHSIZE

./models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
./examples/_temp/imagenet_val.prototxt
./examples/_temp/features
```
./build/tools/extract_features.bin models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel examples/_temp/imagenet_val.prototxt fc7 examples/_temp/features 10 lmdb GPU
```

将特征转化为.mat文件
安装CAFFE的python依赖库，并使用以下两个辅助文件把lmdb转换为mat。

./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)

运行bash输出.mat文件


#!/usr/bin/env sh

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

参考：
https://blog.csdn.net/lijiancheng0614/article/details/48180331