ubuntu16.04 使用tensorflow object detection训练自己的模型

sudo apt-get install pyqt4-dev-tools

sudo apt-get install pyqt5-dev-tools

sudo apt-get install python-lxml

cd labelImg-master
make all

python labelImg.py

import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
pathStr = r‘/home/somnus/boat/train‘
os.chdir(pathStr)
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‘).find(‘width‘).text),
                     int(root.find(‘size‘).find(‘height‘).text),
                     member.find(‘name‘).text,
                     int(member.find(‘bndbox‘).find(‘xmin‘).text),
                     int(member.find(‘bndbox‘).find(‘ymin‘).text),
                     int(member.find(‘bndbox‘).find(‘xmax‘).text),
                     int(member.find(‘bndbox‘).find(‘ymax‘).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 = os.path.join(os.getcwd(), ‘annotations‘)
    image_path = pathStr
    xml_df = xml_to_csv(image_path)
    xml_df.to_csv(‘boat_train.csv‘, index=None)
    print(‘Successfully converted xml to csv.‘)
main()

"""
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

#########根据需要修改路径
os.chdir(‘/home/somnus/models/reserach/object_detection‘)

flags = tf.app.flags
flags.DEFINE_string(‘csv_input‘, ‘‘, ‘Path to the CSV input‘)
flags.DEFINE_string(‘output_path‘, ‘‘, ‘Path to output TFRecord‘)
flags.DEFINE_string(‘image_dir‘, ‘‘, ‘Path to images‘)
FLAGS = flags.FLAGS


####根据需要修改标签
def class_text_to_int(row_label):
    if row_label == ‘car‘:
        return 1
    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)

    #####根据需要修改训练集或测试集图片路径
    path = os.path.join(‘images/train‘)

    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()

python generate_tfrecord.py --csv_input=data/car_train.csv  --output_path=data/car_train.record
python generate_tfrecord.py --csv_input=data/car_val.csv  --output_path=data/car_val.record

item {
  id: 1
  name: ‘car‘
}

model {
  ssd {

  #根据需要修改训练的数据类数
    num_classes: 1

    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: {

 #根据需要修改训练批次
  batch_size: 24


  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
    }
  }
  #这两行注释
  #fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
  #from_detection_checkpoint: true

  # 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 {

  #修改路径
  input_path: "data/car_train.record"

  }

 #修改路径
  label_map_path: "data/mymodel_label_map.pbtxt"

}

eval_config: {
  num_examples: 200
  # 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 {
   
   #修改路径
   input_path: "data/car_val.record"
  
}
  
  #修改路径
  label_map_path: "data/mymodel_label_map.pbtxt"
 
  shuffle: false
  num_readers: 1
}

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

python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/ssd_mobilenet_v1_coco.config --trained_checkpoint_prefix training/model.ckpt-8004 --output_directory car_inference_graph