tensorflow 异常检测实现 Java tensorflow object detection api

训练自己的模型

• 一、创建训练集和测试集

• 1.创建images文件夹
• 2.使用labelImg标注工具进行标注

• 二、创建自己的数据集

• 1.将.xml文件转换成.csv文件
• 2.将csv文件转化为TFRecord文件

• 三、下载预训练模型和配置文件

• 1.预训练模型下载
• 2.配置文件
• 3.创建标签文件

• 四、训练
• 五、可能遇到的问题

• 1.显存不够

一、创建训练集和测试集

1.创建images文件夹

在object_detection目录下创建images文件夹，在images文件夹下创建test和train文件夹。

2.使用labelImg标注工具进行标注

下载labelImg，下载地址 。下载完成后解压。打开anaconda prompt cd到刚刚解压目录下E:\labelImg\labelImg-master。然后安装pyqt，安装命令：

conda install pyqt=5

安装完成后执行：

pyrcc5 -o resources.py resources.qrc

不返回任何结果说明没有出错

最后输入python labelImg.py打开labelImg标注工具

在data文件夹下有一个predefined_classes.txt里面包含类别可以修改

快捷键：

Ctrl + s 保存

Ctrl + d 复制当前标签和矩形框

space 将当前图像标记为已验证

w 创建一个矩形框

d 下一张图片

a 上一张图片

del 删除选定的矩形框

Ctrl++ 放大

Ctrl-- 缩小

↑→↓← 键盘箭头移动选定的矩形框

二、创建自己的数据集

1.将.xml文件转换成.csv文件

标注保存完成后会自动生成一个和图片同名的xml文件，我们要把xml文件转换成csv文件，脚本如下：

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()
        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():
    for folder in ['train','test']:
        image_path = os.path.join(os.getcwd(), ('images/' + folder))  #这里就是需要访问的.xml的存放地址
        xml_df = xml_to_csv(image_path)                               # object_detection/images/train or test
        xml_df.to_csv(('images/' + folder + '_labels.csv'), index=None)
        print('Successfully converted xml to csv.')


main()

把上面代码命名为xml_to_csv.py放在object_detection文件夹下面，cd到object_detection输入python xml_to_csv.py 将在images文件夹下产生两个.csv文件，分别为train_labels.csv和test_labels.csv

2.将csv文件转化为TFRecord文件

"""
Usage:
  # From tensorflow/models/
  # Create train data:
  python generate_tfrecord.py --csv_input=images/train_labels.csv --image_dir=images/train --output_path=train.record

  # Create test data:
  python generate_tfrecord.py --csv_input=images/test_labels.csv  --image_dir=images/test --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('image_dir', '', 'Path to the image directory')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS


# M1，this code part need to be modified according to your real situation修改类别
def class_text_to_int(row_label):
    if row_label == 'cup':
        return 1
    elif row_label == 'book':
        return 2
    else:
        None


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(), 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.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()

上面的代码命名为generate_tfrecord.py放在object_detection文件夹下面，然后在此文件夹下运行

python generate_tfrecord.py --csv_input=images/train_labels.csv --image_dir=images/train --output_path=train.record

python generate_tfrecord.py --csv_input=images/test_labels.csv  --image_dir=images/test --output_path=test.record

三、下载预训练模型和配置文件

1.预训练模型下载

下载到object_detection文件夹下并解压，这里选用ssd_mobilenet_v1_coco速度最快

2.配置文件

自己在object_detection文件夹下建立training文件夹，把配置文件放进去

# SSD with Mobilenet v1 configuration for MSCOCO Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.

model {
  ssd {
    num_classes: 1#类别数目根据实际进行修改
    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 {
      }
    }
    anchor_generator {
      ssd_anchor_generator {
        num_layers: 6
        min_scale: 0.2
        max_scale: 0.95
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 3.0
        aspect_ratios: 0.3333
      }
    }
    image_resizer {
      fixed_shape_resizer {
        height: 300
        width: 300
      }
    }
    box_predictor {
      convolutional_box_predictor {
        min_depth: 0
        max_depth: 0
        num_layers_before_predictor: 0
        use_dropout: false
        dropout_keep_probability: 0.8
        kernel_size: 1
        box_code_size: 4
        apply_sigmoid_to_scores: false
        conv_hyperparams {
          activation: RELU_6,
          regularizer {
            l2_regularizer {
              weight: 0.00004
            }
          }
          initializer {
            truncated_normal_initializer {
              stddev: 0.03
              mean: 0.0
            }
          }
          batch_norm {
            train: true,
            scale: true,
            center: true,
            decay: 0.9997,
            epsilon: 0.001,
          }
        }
      }
    }
    feature_extractor {
      type: 'ssd_mobilenet_v1'
      min_depth: 16
      depth_multiplier: 1.0
      conv_hyperparams {
        activation: RELU_6,
        regularizer {
          l2_regularizer {
            weight: 0.00004
          }
        }
        initializer {
          truncated_normal_initializer {
            stddev: 0.03
            mean: 0.0
          }
        }
        batch_norm {
          train: true,
          scale: true,
          center: true,
          decay: 0.9997,
          epsilon: 0.001,
        }
      }
    }
    loss {
      classification_loss {
        weighted_sigmoid {
        }
      }
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 0
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    normalize_loss_by_num_matches: true
    post_processing {
      batch_non_max_suppression {
        score_threshold: 1e-8
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SIGMOID
    }
  }
}
############################################################
train_config: {
  batch_size: 2#不要太大
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 800720
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  #fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"   #可以注释掉
  #from_detection_checkpoint: true                            #注释掉
  # Note: The below line limits the training process to 200K steps, which we
  # empirically found to be sufficient enough to train the pets dataset. This
  # effectively bypasses the learning rate schedule (the learning rate will
  # never decay). Remove the below line to train indefinitely.
  num_steps: 200000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "data/train.record"    #训练集所在位置
  }
  label_map_path: "data/cup.pbtxt"    #标签所在地址
}

eval_config: {
  num_examples: 9         #验证集数量
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 10
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "data/test.record"    #验证集所在地址
  }
  label_map_path: "data/cup.pbtxt"     #标签
  shuffle: false
  num_readers: 1
}

3.创建标签文件

在data文件夹下面新建cup.pbtxt

item {
  id: 1
  name: 'cup'
}

四、训练

在object_detection下面运行

python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_coco.config

出现下面界面，说明训练开始了。

五、可能遇到的问题

1.显存不够

可能是自己拍的图片太大的问题，我刚开始拍的图片一张2MB，显示显存不够。我们可以用如下方法调节图片大小：

右击图片，点击编辑，选择重新调整大小，

改一下数值就能改变大小了