【caffe】feature map可视化

主要参考于http://caffe.berkeleyvision.org/gathered/examples/feature_extraction.html，查看LeNet首个卷积层的feature map输出

需要已经有：

1. 训练完成的.caffemodel文件
2. 网络结构.prototxt
3. 特定feature map的blob名称，通常是prototxt中某一layer的top
4. 需要查看的batch数量

主要步骤包括：

1. 将特定层的feature map生成lmdb文件
2. 转化成mat格式
3. 转化成数组／图片

生成lmdb文件

./build/tools/extract_features examples/mnist/lenet_iter_10000.caffemodel examples/mnist/lenet.prototxt conv1 ./extract/myconv1 10 lmdb GPU 1

将.lmdb文件转化为.mat文件

1. 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)

2. 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)

python lmdb2mat.py ./extract/myconv1/ 64 10 11520 ./extract/myconv1.mat

其中11520=24*24*20（feature map）
*64（batch中的图片数）*10（10个batch）

查看数组值

import scipy.io
matfile='./myconv1.mat'
data=scipy.io.loadmat(matfile)
print(data)	#这里能看到data是一个字典，选取其中的array打印即可看到维度是64*11520.