安装
首先下载TF models，官网地址：https://github.com/tensorflow/models
Research目录下包含了Object Detection这个API。
官方安装指南：
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md
安装很简单，按着官方指南一步步来就可以了。
数据集处理
我的数据是VOC的格式，自己新建一个目录用来存放自己的数据，然后在这个目录下将.xml文件放在xml_file文件夹下，.jpg图片放在images文件夹下。
将数据分成三部分：train、test、validation。贴上代码：
import os
import random
import time
import shutil
xmlfilepath=r'xml_file'
saveBasePath=r"./Annotations"
trainval_percent=0.9
train_percent=0.85
total_xml = os.listdir(xmlfilepath)
num=len(total_xml)
list=range(num)
tv=int(num*trainval_percent)
tr=int(tv*train_percent)
trainval= random.sample(list,tv)
train=random.sample(trainval,tr)
print("train and val size",tv)
print("train size",tr)
start = time.time()
test_num=0
val_num=0
train_num=0
for i in list:
name=total_xml[i]
if i in trainval:
if i in train:
directory="train"
train_num+=1
xml_path=os.path.join(os.getcwd(),'Annotations/{}'.format(directory))
if(not os.path.exists(xml_path)):
os.mkdir(xml_path)
filePath=os.path.join(xmlfilepath,name)
newfile=os.path.join(saveBasePath,os.path.join(directory,name))
shutil.copyfile(filePath, newfile)
else:
directory="validation"
xml_path=os.path.join(os.getcwd(),'Annotations/{}'.format(directory))
if(not os.path.exists(xml_path)):
os.mkdir(xml_path)
val_num+=1
filePath=os.path.join(xmlfilepath,name)
newfile=os.path.join(saveBasePath,os.path.join(directory,name))
shutil.copyfile(filePath, newfile)
else:
directory="test"
xml_path=os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))
if(not os.path.exists(xml_path)):
os.mkdir(xml_path)
test_num+=1
filePath=os.path.join(xmlfilepath,name)
newfile=os.path.join(saveBasePath,os.path.join(directory,name))
shutil.copyfile(filePath, newfile)
end = time.time()
seconds=end-start
print("train total : "+str(train_num))
print("validation total : "+str(val_num))
print("test total : "+str(test_num))
total_num=train_num+val_num+test_num
print("total number : "+str(total_num))
print( "Time taken : {0} seconds".format(seconds))执行完之后会产生一个Annotations目录，这个目录下有train、test、validation三个目录，每个目录下有分好的.xml文件。
将.xml转换成.csv。新建csv文件夹，用来存放.csv文件。代码，注意路径：
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
def xml_to_csv(path):
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
print(root.find('filename').text)
for member in root.findall('object'):
value = (root.find('filename').text,
int(root.find('size')[0].text), #width
int(root.find('size')[1].text), #height
member.find('name').text,
int(member.find('bndbox')[0].text),
int(member.find('bndbox')[1].text),
int(member.find('bndbox')[2].text),
int(member.find('bndbox')[3].text),
)
xml_list.append(value)
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
def main():
for directory in ['train','test','validation']:
xml_path = os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))
xml_df = xml_to_csv(xml_path)
xml_df.to_csv('csv/ngy_{}_labels.csv'.format(directory), index=None)
print('Successfully converted xml to csv.')
main()将.csv转成.tfrecord，注意要改一下label，改成你自己数据集的label，代码，注意路径：
"""
Usage:
# From tensorflow/models/
# Create train data:
python generate_tfrecord.py --csv_input=data/train_labels.csv --output_path=train.record
# Create test data:
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record
"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
import tensorflow as tf
from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict
flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS
# TO-DO replace this with label map
def class_text_to_int(row_label):
if row_label == 'car':
return 1
elif row_label == 'umbrellaman':
return 2
elif row_label == 'cone':
return 3
elif row_label == 'person':
return 4
else:
return 0
def split(df, group):
data = namedtuple('data', ['filename', 'object'])
gb = df.groupby(group)
return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
def create_tf_example(group, path):
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def main(_):
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
path = os.path.join(os.getcwd(), 'images')
examples = pd.read_csv(FLAGS.csv_input)
grouped = split(examples, 'filename')
num=0
for group in grouped:
num+=1
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
print(num)
writer.close()
output_path = os.path.join(os.getcwd(), FLAGS.output_path)
print('Successfully created the TFRecords: {}'.format(output_path))
if __name__ == '__main__':
tf.app.run()然后用一个脚本来执行，修改下自己的路径：
#!/bin/bash
python3 csv_to_tfrecords.py --csv_input=csv/ngy_train_labels.csv --output_path=csv/ngy_train.tfrecord
python3 csv_to_tfrecords.py --csv_input=csv/ngy_test_labels.csv --output_path=csv/ngy_test.tfrecord
python3 csv_to_tfrecords.py --csv_input=csv/ngy_validation_labels.csv --output_path=csv/ngy_validation.tfrecord就可以得到train、test、validation的tfrecords。
创建标签文件
将.tfrecord文件放在你想放的目录下，
在object_detection目录下创建自己的目录，我自己建了training/ssd_inception_v2_ngy目录，
在该目录下创建ngy_label_map.pbtxt，写入类别标签，跟之前的对应就行：
item {
id: 1
name: 'car'
}
item {
id: 2
name: 'umbrellaman'
}
item {
id: 3
name: 'cone'
}
item {
id: 4
name: 'person'
}下载预训练模型
这个页面有许多模型可供下载，这里我选择ssd_inception_v2：
修改配置文件
找到samples/configs目录下的ssd_inception_v2_coco.config，复制到ssd_inception_v2_ngy目录下，修改配置，注意类别数目和自己的各种路径：
num_classes: 4fine_tune_checkpoint: "ssd_inception_v2_coco_2017_11_17/model.ckpt"train_input_reader: {
tf_record_input_reader {
input_path: "data/ngy_train.tfrecord"
}
label_map_path: "training/ssd_inception_v2_ngy/ngy_label_map.pbtxt"
}eval_input_reader: {
tf_record_input_reader {
input_path: "data/ngy_validation.tfrecord"
}
label_map_path: "training/ssd_inception_v2_ngy/ngy_label_map.pbtxt"
shuffle: false
num_readers: 1
}开始训练
执行脚本：
python train.py \
--train_dir=training/ssd_inception_v2_ngy \
--pipeline_config_path=training/ssd_inception_v2_ngy/ssd_inception_v2_coco.config \如果一切正常就会看到每一步的loss。
evaluation
可以使用eval.py一边训练一边eval。
但是我显存不够了，查到网上有人用一种方法也可以eval：用cpu来eval。
进eval.py，添加一行代码：
os.environ["CUDA_VISIBLE_DEVICES"]=""将gpu device设为空，就可以使用cpu进行eval。
修改一下ssd_inception_v2_ngy/ssd_inception_v2_coco.config文件：
eval_config: {
num_examples: 2519
num_visualizations: 10参数大小根据实际情况设定。
如果训练完了再eval，那程序可能会一直挂那，卡着不动。貌似是官方的一个bug，它要检测出一个新的checkpoint生成再eval，如果训练完是没有新的checkpoint生成的所以会挂那。好像有人解决了这个问题，是在eval_util.py文件中加一行代码：
logging.basicConfig(level=logging.INFO)导出模型
创建目录：object_detection/inference_graph/ssd_ngy_inference_graph，用来存放导出的模型
执行脚本：
#!/bin/bash
python3 export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path training/ssd_inception_v2_ngy/ssd_inception_v2_coco.config \
--trained_checkpoint_prefix training/ssd_inception_v2_ngy/model.ckpt-153376 \
--output_directory inference_graph/ssd_ngy_inference_graph/153376demo
有一个object_detection_tutorial.ipynb，打开notebook进去改改，把加载模型路径换成自己训练的结果，然后下面那个执行程序它是批量的，自己改成单张就好了，这步比较简单，不说了。当然，改成摄像头程序也是可行的。
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
