objectdetection训练自己的数据

1. 将数据转为tfrecord

    首先将数据转为csv，参考网址忘记了，不好意思。

# -*- coding: utf-8 -*-
"""
Created on Tue Jan 16 00:52:02 2018
@author: Xiang Guo
"""

import os
import glob

import sys
sys.path.append("..")
import pandas as pd
import xml.etree.ElementTree as ET

os.chdir('/data/identitycard/VOCtrainval_06-Nov-2007/Annotations')   //训练数据集的xml
path = '/data/identitycard/VOCtrainval_06-Nov-2007/Annotations'   //训练数据集的xml

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('/data/identitycard/csv/identitycard_6_train_labels.csv',  index=None)  //保存csv的路径
    print('Successfully converted xml to csv.')


main()

其次转为tfrecord,参考的网址忘记了，不好意思

# -*- coding: utf-8 -*-
"""
Created on Tue Jan 16 01:04:55 2018
@author: Xiang Guo
"""

"""
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

import sys
sys.path.append("..")

from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict

os.chdir('/home/models/research/object_detection/')

flags = tf.app.flags
flags.DEFINE_string('csv_input', '/data/identitycard/csv/identitycard_6_train_labels.csv', 'Path to the CSV input') //csv路径
flags.DEFINE_string('output_path', '/data/identitycard/object_detection_tfrecord/train_6.record', 'Path to output TFRecord')//保存tfrecord路径
FLAGS = flags.FLAGS


# TO-DO replace this with label map
def class_text_to_int(row_label):   //类别信息
    if row_label == 'name':
        return 1
    elif row_label == 'gender':
        return 2
    elif row_label == 'nationality':
        return 3
    elif row_label == 'birth':
        return 4
    elif row_label == 'address':
        return 5
    elif row_label == 'idnumber':
        return 6
    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(_):
    os.environ["CUDA_VISIBLE_DEVICES"] = "0"

    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
    path = os.path.join(os.getcwd(), 'images')
    path="/data/identitycard/VOCtrainval_06-Nov-2007/JPEGImages"  //训练数据集图片
    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()

2. 修改网络参数信息

    首先修改 data/pascal_label_map.pbtxt，  里面为要检测的类别信息

    其次修改samples/configs/xxxxxxxxx.config，里面为训练的网络

    例如：ssd_mobilenet_v2_coco.config

# SSD with Mobilenet v2 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 #修改类别
    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_v2'
      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: 3
      }
      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: 16
  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
    }
  }

 #不需要fine——tune,可将其注释掉
  #fine_tune_checkpoint: "/data/liuyan/identitycard/model/fineturn_model/ssd_mobilenet_v2_coco_2018_03_29/model.ckpt"   
  #fine_tune_checkpoint_type:  "detection"
  # 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: 40000   #迭代次数
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "/data/car_plate/objent_detection_tfrecord/train.record"  
      #训练数据的tfrecord路径
  }
  label_map_path: "/home/models/research/object_detection/data/pascal_label_map.pbtxt" #类别信息
}

eval_config: {
  num_examples: 8000
  # 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/car_plate/objent_detection_tfrecord/train.record" #验证数据的tfrecord路径
  }
  label_map_path: "/home/models/research/object_detection/data/pascal_label_map.pbtxt"#类别信息
  shuffle: false
  num_readers: 1
}

3. 训练模型

    修改 ：utils/train.py

flags.DEFINE_string('train_dir', '/data/identitycard/object_detection_ssd_model_6/',
                    'Directory to save the checkpoints and training summaries.')#保存模型

flags.DEFINE_string('pipeline_config_path', '/home/models/research/object_detection/samples/configs/ssd_mobilenet_v2_coco.config',
                    'Path to a pipeline_pb2.TrainEvalPipelineConfig config '
                    'file. If provided, other configs are ignored')  #指定config

 

4. 转为pb模型

export_inference_graph.py

flags.DEFINE_string('pipeline_config_path', '/home/models/research/object_detection/samples/configs/ssd_mobilenet_v2_coco.config',
                    'Path to a pipeline_pb2.TrainEvalPipelineConfig config '
                    'file.')
flags.DEFINE_string('trained_checkpoint_prefix', '/data/car_plate/object_ssd_model/model.ckpt-20000',
                    'Path to trained checkpoint, typically of the form '
                    'path/to/model.ckpt')
flags.DEFINE_string('output_directory', '/data/car_plate/object_detection_pb2_test', 'Path to write outputs.')

 

5. 查看模型检测结果

  utils/object_detection_tutorial.ipynb