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)
leveldb2mat.py
import leveldb
import feat_helper_pb2
import numpy as np
import scipy.io as sio
import time
def main(argv):
leveldb_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 = leveldb.LevelDB(leveldb_name)
datum = feat_helper_pb2.Datum()
ft = np.zeros((window_num, int(sys.argv[4])))
for im_idx in range(window_num):
datum.ParseFromString(db.Get('%d' %(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!'
#leveldb.DestroyDB(leveldb_name)
if __name__ == '__main__':
import sys
main(sys.argv)
#!/usr/bin/env sh # args for EXTRACT_FEATURE TOOL=../../build/tools MODEL=../../examples/imagenet/caffe_reference_imagenet_model #下载得到的caffe model PROTOTXT=../../examples/_temp/imagenet_val.prototxt # 网络定义 LAYER=conv1 # 提取层的名字，如提取fc7等 LEVELDB=../../examples/_temp/features_conv1 # 保存的leveldb路径 BATCHSIZE=10 # args for LEVELDB to MAT DIM=290400 # 需要手工计算feature长度 OUT=../../examples/_temp/features.mat #.mat文件保存路径 BATCHNUM=1 # 有多少哥batch， 本例只有两张图， 所以只有一个batch $TOOL/extract_features.bin $MODEL $PROTOTXT $LAYER $LEVELDB $BATCHSIZE python leveldb2mat.py $LEVELDB $BATCHNUM $BATCHSIZE $DIM $OUT
