前奏--学生党记录,大佬勿喷
一、准备tensorflow的安装环境
1、Anaconda3(笔者装的minconda,Miniconda,顾名思义,它只包含最基本的内容——python与conda,以及相关的必须依赖项,对于空间要求严格的用户,Miniconda是一种选择。就只包含最基本的东西,其他的库得自己装;Anaconda则是一个打包的集合,里面预装好了conda、某个版本的python、众多packages、科学计算工具等等,就是把很多常用的不常用的库都给你装好了)
2、tensorflow1.x(需要1.12版本以上,笔者装的1.13,对应的cuda和cudnn版本一定要注意匹配,如下图)
3、激活tensorflow环境,按照如下链接进行安装
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md
按照步骤一步步来装,cocoapi也需要装好
二、准备数据集
参考下面链接
https://www.cnblogs.com/zongfa/p/9663649.html
https://blog.csdn.net/qq_17854471/article/details/89786400
三、转换成tensorflow能识别的格式
1、统计xml文件有多少类别
import xml.dom.minidom as xmldom
import os
#voc数据集获取所有标签的所有类别数"
annotation_path="/home/chenxin/下载/Annotations"
annotation_names=[os.path.join(annotation_path,i) for i in os.listdir(annotation_path)]
labels = list()
for names in annotation_names:
xmlfilepath = names
domobj = xmldom.parse(xmlfilepath)
# 得到元素对象
elementobj = domobj.documentElement
#获得子标签
subElementObj = elementobj.getElementsByTagName("object")
for s in subElementObj:
label=s.getElementsByTagName("name")[0].firstChild.data
#print(label)
if label not in labels:
labels.append(label)
print(labels)
2、xml转csv格式(只需识别一个类别)
# -*- coding:utf-8 -*-
#!/usr/bin/env python
"""
@Time: 2020/2/10 22:00
@Author: chenxin
@File Name: Only_one_label_xml2csv.py
@Software: PyCharm
"""
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
## xml文件的路径
os.chdir(‘/home/chenxin/models-master/research/object_detection/images/train1‘)
path = ‘/home/chenxin/models-master/research/object_detection/images/train1‘
img_path = ‘/home/chenxin/models-master/research/object_detection/images/train1‘
def xml_to_csv(path):
xml_list = []
for xml_file in glob.glob(path + ‘/*.xml‘): # 返回所有匹配的文件路径列表即对于path目录下的每一个xml文件
tree = ET.parse(xml_file)#获得xml对应的解析树
root = tree.getroot()#获得根标签annotation
for member in root.findall(‘object‘):#对于每一个object标签
value = (root.find(‘filename‘).text,#在根标签下查找filename标签,并获得其文本信息
#int(root.find(‘size‘)[0].text),#在根标签下查找size标签,并获得size的第0个子标签(width)的文本信息,并转化为int
#int(root.find(‘size‘)[1].text),#在根标签下查找size标签,并获得size的第1个子标签(width)的文本信息,并转化为int
member[0].text, # 获得object的第0个子标签(name)的文本信息
float(member[4][0].text),#获得object的第4个子标签(bndbox),并获得bndbox的第0个子标签(xmin)的文本信息,并转换为int
float(member[4][1].text),#获得object的第4个个子标签(bndbox),并获得bndbox的第1个子标签(ymin)的文本信息,并转换为int
float(member[4][2].text),#获得object的第4个个子标签(bndbox),并获得bndbox的第2个子标签(xmax)的文本信息,并转换为int
float(member[4][3].text) #获得object的第4个个子标签(bndbox),并获得bndbox的第3个子标签(ymax)的文本信息,并转换为int
)
# value = (img_path + ‘/‘ + root.find(‘filename‘).text,
# int(member[1][0].text),
# int(member[1][1].text),
# int(member[1][2].text),
# int(member[1][3].text),
# member[0].text
# )
xml_list.append(value)
# column_name = [‘filename‘, ‘width‘, ‘height‘, ‘class‘, ‘xmin‘, ‘ymin‘, ‘xmax‘, ‘ymax‘]
column_name = [‘filename‘, ‘xmin‘, ‘ymin‘, ‘xmax‘, ‘ymax‘, ‘class‘]
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
if __name__ == ‘__main__‘:
#for folder in [‘train‘,‘test‘]:
# image_path = os.path.join(os.getcwd(),(‘images/‘+folder))
# xml_path = xml_to_csv(image_path)
# xml_df.to_csv((‘images/‘+folder+‘_‘labels.csv‘),index = None
image_path = path
xml_df = xml_to_csv(image_path)
## 修改文件名称
xml_df.to_csv((‘/home/chenxin/models-master/research/object_detection/images/train1/‘+‘train1.csv‘), index=None)
print(‘Successfully converted xml to csv.‘)
3、xml转csv格式(需识别两个及以上类别)
# coding: utf-8
import glob
import pandas as pd
import xml.etree.ElementTree as ET
classes = ["person","hat"]
def xml_to_csv(path):
train_list = []
eval_list = []
for cls in classes:
xml_list = []
# 读取注释文件
for xml_file in glob.glob(path + ‘/*.xml‘):
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall(‘object‘):
if cls == member[0].text:
value = (root.find(‘filename‘).text,
int(root.find(‘size‘)[0].text),
int(root.find(‘size‘)[1].text),
member[0].text,
float(member[4][0].text),
float(member[4][1].text),
float(member[4][2].text),
float(member[4][3].text)
)
xml_list.append(value)
for i in range(0, int(len(xml_list) * 0.9)):
train_list.append(xml_list[i])
for j in range(int(len(xml_list) * 0.9) + 1, int(len(xml_list))):
eval_list.append(xml_list[j])
column_name = [‘filename‘, ‘width‘, ‘height‘, ‘class‘, ‘xmin‘, ‘ymin‘, ‘xmax‘, ‘ymax‘]
# 保存为CSV格式
train_df = pd.DataFrame(xml_list, columns=column_name)
eval_df = pd.DataFrame(eval_list, columns=column_name)
train_df.to_csv(‘/home/chenxin/models-master/research/object_detection/images/data/train531.csv‘, index=None)
eval_df.to_csv(‘/home/chenxin/models-master/research/object_detection/images/data/eval531.csv‘, index=None)
def main():
# path = ‘E:\\\data\\\Images‘
path = r‘/home/chenxin/models-master/research/object_detection/images/train531‘ # path参数更具自己xml文件所在的文件夹路径修改
xml_to_csv(path)
print(‘Successfully converted xml to csv.‘)
main()
4、csv转record格式
(终端运行版:python generate_tfrecord.py --csv_input=/home/chenxin/models-master/research/object_detection/images/data/train.csv --output_path=/home/chenxin/models-master/research/object_detection/images/data/train.record)
# generate_tfrecord.py
# -*- coding: utf-8 -*-
#!/usr/bin/env python
"""
@Time: 2020/2/10 22:00
@Author: chenxin
@File Name: csv2tfrecord.py
@Software: PyCharm
"""
"""
Usage:
# From tensorflow/models/
# Create train data:
python generate_tfrecord.py --csv_input=/home/chenxin/models-master/research/object_detection/images/data/train.csv --output_path=/home/chenxin/models-master/research/object_detection/images/data/train.record
# Create test data:
python generate_tfrecord.py --csv_input=/home/chenxin/models-master/research/object_detection/images/data/test.csv --output_path=/home/chenxin/models-master/research/object_detection/images/data/test.record
"""
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
os.chdir(‘/home/chenxin/models-master/research/object_detection‘)
flags = tf.app.flags
flags.DEFINE_string(‘csv_input‘,‘‘,‘Path to CSV input‘)
flags.DEFINE_string(‘out_path‘,‘‘,‘Path to output TFRecord‘)
FLAGS = flags.FLAGS
def class_text_to_int(row_label):
if row_label == ‘hat‘:
return 1
if row_label == ‘person‘:
return 2
else :
return 3
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(self):
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
path = os.path.join(os.grtcwd(),FLAGS.image_dir)
examples = pd.read_csv(FLAGS.csv_input)
grouped = split(examples,‘filename‘)
for group in grouped:
tf_example = create_tf_example(group,path)
writer.write(tf_example.SerialzeToString())
writer.close()
output_path = os.path.join(os.getcwd(), FLAGS.output_path)
#output_path = os.path.join(os.getcwd(),‘images/data‘)
print(‘Successfully created the TFRecords:{}‘.format(output_path))
if __name__ == ‘__main__‘:
tf.app.run()
四、配置文件和下载模型
1、 xml位置:/home/chenxin/models-master/research/object_detection/images/xml
2、 xml2csv文件位置:/home/chenxin/models-master/research/object_detection/images/data(自定义)
3、 csv2tfrecord文件位置:/home/chenxin/models-master/research/object_detection/images/data(自定义)
4、 在官方提供的model zoo里下载训练好的模型。我们使用ssd_mobilenet_v1_coco,先下载它。
在 object_dection文件夹下,解压ssd_mobilenet_v1_coco.tar.gz
模型存放位置:mask_rcnn_inception_v2_coco:/home/chenxin/models-master/research/object_detection/
5、建立training文件夹:将ssd_mobilenet_v1_coco.config 放在training 文件夹下
training文件位置:/home/chenxin/models-master/research/object_detection/training
进行如下更改:
5.1、搜索其中的 PATH_TO_BE_CONFIGURED ,将对应的路径改为自己的路径;
注意最后train input reader和evaluation input reader中label_map_path必须保持一致。
5.2、将 num_classes 按照实际情况更改,我的例子中是1;
5.3、batch_size 原本是24,我在运行的时候出现显存不足的问题,为了保险起见,改为1,如果1还是出现类似问题的话,建议换电脑……
5.4、fine_tune_checkpoint: "ssd_mobilenet_v1_coco/model.ckpt"
from_detection_checkpoint: true
(pipeline.config里面标红的都是需要更改的)
model {
ssd {
num_classes: 2
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
feature_extractor {
type: "ssd_mobilenet_v1"
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999999e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.029999999
}
}
activation: RELU_6
batch_norm {
decay: 0.99970001
center: true
scale: true
epsilon: 0.001
train: true
}
}
use_depthwise: true
}
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
box_predictor {
convolutional_box_predictor {
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999999e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.029999999
}
}
activation: RELU_6
batch_norm {
decay: 0.99970001
center: true
scale: true
epsilon: 0.001
train: true
}
}
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.80000001
kernel_size: 3
box_code_size: 4
apply_sigmoid_to_scores: false
use_depthwise: true
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.94999999
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.33329999
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 9.9999999e-09
iou_threshold: 0.60000002
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
normalize_loss_by_num_matches: true
loss {
localization_loss {
weighted_smooth_l1 {
}
}
classification_loss {
weighted_sigmoid {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99000001
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
}
}
train_config {
batch_size: 1
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
optimizer {
rms_prop_optimizer {
learning_rate {
exponential_decay_learning_rate {
initial_learning_rate: 0.0040000002
decay_steps: 800720
decay_factor: 0.94999999
}
}
momentum_optimizer_value: 0.89999998
decay: 0.89999998
epsilon: 1.0
}
}
fine_tune_checkpoint: "/home/chenxin/models-master/research/object_detection/mask_rcnn_inception_v2_coco/model.ckpt"
from_detection_checkpoint: true
num_steps: 20000
}
train_input_reader {
label_map_path: "/home/chenxin/models-master/research/object_detection/images/data/chenxin.pbtxt"
tf_record_input_reader {
input_path: "/home/chenxin/models-master/research/object_detection/images/data/train.record"
}
}
eval_config {
num_examples: 20
max_evals: 10
retain_original_images: true
}
eval_input_reader {
label_map_path: "/home/chenxin/models-master/research/object_detection/images/data/chenxin.pbtxt"
shuffle: false
num_readers: 1
tf_record_input_reader {
input_path: "/home/chenxin/models-master/research/object_detection/images/data/eval.record"
}
}
6、在前面xml2csv文件夹(/data)下,创建一个 xxx.pbtxt的文本文件(这个id顺序要与前面生成tfrecod的py文件代码顺序一样)
item{
id:1
name:‘hat‘
}
item{
id:2
name:‘person‘
}
五、训练模型
1、本地GPU训练(本机环境:Ubuntu 18.04),终端进入 object_detection目录下,最新版用model_main.py
2、如果是python3训练,添加list()
到 model_lib.py的大概390行category_index.values()变成:
list(category_index.values()),否则会有 can‘t pickle dict_values ERROR出现
3、准备好所有后,在终端输入如下命令:
python model_main.py --logtostderr --model_dir=/home/chenxin/model-master/research/object_detection/trainning/ --pipeline_config_path=/home/chenxin/model-master/research/object_detection/trainning/ssd_mobilenet_v1_coco.config
4、另开一个终端,同样进入到object_detection目录下,输入:
tensorboard --logdir=training
5、运行一段时间后,我们可以看到我们的training文件夹下已经有模型数据保存了,接下来就可以生成我们的需要的模型文件了,终端在object_detection目录下,输入:
python3 export_inference_graph.py --input_type image_tensor --pipeline_config_path /home/chenxin/models-master/research/object_detection/training/ssd_mobilenet_v1_coco.config --trained_checkpoint_prefix /home/chenxin/models-master/research/object_detection/training/model.ckpt-11945 --output_directory ssd_mobilenet_v1_coco
其中,trained checkpoint 后面接着的数字改为如上图里面的任意一个数字, output为想要将模型存放在何处,新建了一个文件夹xxx_detction 。运行结束后,就可以在xxx_detction文件夹下看到若干文件,有saved_model、checkpoint、frozen_inference_graph.pb等。 .pb结尾的就是最重要的frozen model.
六、测试模型
1、将object_detection目录下的object_detection_tutorial.ipynb打开
2、不用下载模型,下载相关代码可以删除,model name, path to labels , num classes 更改成自己的,download model部分都删去。
3、将训练好的模型放到自定义位置,我的文件位置:/home/chenxin/文档/ssd_mobilenet_v1_coco,测试图片,准备几张放入/home/chenxin/文档/mask_rcnn/test images文件夹中,命名images+数字.jpg的格式,就不用改代码,再在ssd_mobilenet_v1_coco里面新建data/文件夹,将xxx.pbtxt
4、一行更改自己图片的数字序列就好了,range(1,10),我的图片命名从1至9.
# For the sake of simplicity we will use only 2 images: # image1.jpg # image2.jpg # If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS. PATH_TO_TEST_IMAGES_DIR = ‘/home/chenxin/文档/ssd_mobilenet_v1_coco/test_images‘ TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, ‘image{}.jpg‘.format(i)) for i in range(1, 10) ]