环境:win10
Anaconda3 tensorflow 1.9.0
【参考】https://blog.csdn.net/dy_guox/article/details/79111949
上篇运行了demo之后,打算训练自己的数据集,但是没有完全成功,不过反复弄了好几次后,这些步骤还是熟了的,把遇到的问题也贴出来,有人会的话帮我解答下
一、准备数据集
数据集用 LabelImg 标注会会生成相应的xml文件,具体不在详述,我是直接找了之前用过的一个车的数据集(300张做训练集,60张做测试集),但是这里除了原图跟xml文件外,还需要.cvs和.record文件,生成这两个文件的python代码如下(参考的博主有提供,这里我做个简单的注释,不懂可以问)
注:.cvs和.record文件这两个文件训练集train和测试集test都需要有,所以下面的代码里修改数据集路径就可以成相应的文件啦,也就是这些python脚本分别要操作训练集跟测试集,最后生成4个文件
1.生成.cvs文件python脚本
#生成.cvs文件pyhon脚本
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 16 00:52:02 2018
@author: Xiang Guo #博主,感谢
将文件夹内所有XML文件的信息记录到CSV文件中
"""
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
os.chdir('D:\\RaniFile\\CarModelYHQ\\test') #数据集路径
path = 'D:\\RaniFile\\CarModelYHQ\\test' #生成的.cvs文件路径
def xml_to_csv(path):
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][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():
image_path = path
xml_df = xml_to_csv(image_path)
xml_df.to_csv('tv_vehicle_labels.csv', index=None) #第一个参数是生成的文件名
print('Successfully converted xml to csv.')
main()
2.生成.recored文件python脚本
代码里原博主非常用心的写了使用方法,我在这里在说一下吧
## --csv_input=参数表示.cvs路径及文件名 --output_path=参数表示生成的文件名
##
python generate_tfrecord.py --csv_input=data/tv_vehicle_labels.csv --output_path=train.record
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record
#生成.recored文件python脚本
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 16 01:04:55 2018
@author: Xiang Guo
由CSV文件生成TFRecord文件
"""
"""
Usage:
# From tensorflow/models/
# Create train data:
python generate_tfrecord.py --csv_input=data/tv_vehicle_labels.csv --output_path=train.record
# Create test data:
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=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('D:\\RaniFile\\myproject\\tensorflow\\models\\research\\object_detection') #这个跟路径下面会用到还会再接一段,包括运行时候参数的路径的路径也是接着这个
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
#注意将对应的label改成自己的类别!!!!!!!!!!
def class_text_to_int(row_label):
if row_label == 'sedan':
return 1
elif row_label == 'van':
return 2
elif row_label == 'SUV':
return 3
elif row_label == 'truck':
return 4
elif row_label == 'minibus':
return 5
elif row_label == 'hatchback':
return 6
elif row_label == 'tricycle':
return 7
elif row_label == 'bus':
return 8
else:
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(), 'myimages\\test') #第二个参数,这个原图路径接着前面那个注释的路径的
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.SerializeToString())
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()
这里面的路径如果有点纠结理不清地话,可以先是这运行下,找不到会报错,然后慢慢改。。。我就是这样的,其实python代码仔细看看也不难理解
3.建一个.pbtxt文件,里面写类别,我的文件名是tv_vehicle_detection.pbtxt
#这个id跟name,要跟上不一个生成.record脚本里面的那个类别一致
item {
id: 1
name: 'sedan'
}
...
...
item {
id: 8
name: 'bus'
}
好了数据集的准备到此就做完了
二、配置文件与模型
先列一下文件夹,这些文件都是 object_detection这个文件夹下,相信运行过demo的同学对这个文件的位置应该很熟悉了
-mydata/
--test_labels.csv #这些文件都在上一步准备好了
--test.record
--train_labels.csv
--train.record
--tv_vehicle_detection.pbtxt
-myimages/
--test/ #测试集图片
---testingimages.jpg
--train/ #训练集图片
---testingimages.jpg
-mytraining
接下来要配置模型文件了
1.下载所需预训练模型COCO-trained models
我用的是ssd_mobilenet_v1_coco_2018_01_28.tar.gz所以下面配置都以它为例讲,下载下来后解压就行
2.把里面的model.ckpt、model.ckpt.data-00000-of-00001、model.ckpt.index这三个文件都放到mydata文件夹下
3.把pipeline.config文件放到mytraining文件夹下,里面一些参数要配置(之后有时间仔细读下这个配置文件,写个注释吧)
model {
ssd {
num_classes: 8 #类别个数,我的标签一共是有8类
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
feature_extractor {
type: "ssd_mobilenet_v1" #模型名称
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.99999989895e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.0299999993294
}
}
activation: RELU_6
batch_norm {
decay: 0.999700009823
center: true
scale: true
epsilon: 0.0010000000475
train: 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: 3.99999989895e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.0299999993294
}
}
activation: RELU_6
batch_norm {
decay: 0.999700009823
center: true
scale: true
epsilon: 0.0010000000475
train: true
}
}
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.800000011921
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.20000000298
max_scale: 0.949999988079
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.333299994469
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 0.300000011921
iou_threshold: 0.600000023842
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: 0.990000009537
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
}
}
train_config { #训练的一些配置
batch_size: 1 #batch_size大小,改成了1,怕显存不足,硬件支持的话可以不改
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: 0.00400000018999
decay_steps: 800720
decay_factor: 0.949999988079
}
}
momentum_optimizer_value: 0.899999976158
decay: 0.899999976158
epsilon: 1.0
}
}
fine_tune_checkpoint: "mydata/model.ckpt"
from_detection_checkpoint: true
num_steps: 200000 #训练迭代次数,当然运行的时候也可以写参数设置
}
train_input_reader {
label_map_path: "mydata/tv_vehicle_detection.pbtxt" #类别路径
tf_record_input_reader {
input_path: "mydata/train.record" #训练集.record文件路径
}
}
eval_config {
num_examples: 8000
max_evals: 10
use_moving_averages: false
}
eval_input_reader {
label_map_path: "mydata/tv_vehicle_detection.pbtxt" #类别路径,同上
shuffle: false
num_readers: 1
tf_record_input_reader {
input_path: "mydata/test.record" #测试集.record文件路径
}
}
好了文件配置也完成了
三、训练模型
Anaconda Prompt 定位到 models\research\object_detection文件夹下,运行如下命令:
python model_main.py
--pipeline_config_path=mytraining/pipeline.config #pipeline.config路径
--model_dir=object_detection/mytraining #生成模型的文件夹
--num_train_steps=20000 #训练20000步
--num_eval_steps=1000 #测试1000步
--alsologtostderr
然后就开始训练了
tensorboard可以可视化训练过程,所以我也试了下, Anaconda Prompt 定位到 models\research\object_detection文件夹下,运行如下命令
tensorboard --logdir='mytraining' #这个文件夹就是存训练好的模型的那个文件夹
路径对的话就可以出来,关于tensordboard可以展示还有很多,不过要在代码里加上你需要统计的信息,我就简单看了下,有兴趣的可以仔细研究尝试
其实我训练到后面还是出了问题。。。。。(训练就很慢了,当时就只留了这张截图,不知道能不能明白问题的意思,有时间在尝试下。。。。)