使用Tensorflow object detection API——訓練模型（Window10系統）

時間 2019-11-09

標籤使用 tensorflow object detection api 訓練模型 window10 window 系統欄目 Windows 简体版

原文原文鏈接

【數據標註處理】python

　　一、先將下載好的圖片訓練數據放在models-master/research/images文件夾下，並分別爲訓練數據和測試數據建立train、test兩個文件夾。文件夾目錄以下ios

　　二、下載 LabelImg 這款小軟件對圖片進行標註git

　　三、下載完成後解壓，直接運行。（注：軟件目錄最好不要存在中文，不然可能會報錯）github

　　四、設置圖片目錄，逐張打開圖片，按快捷鍵W，而後經過鼠標拖拽實現目標物體框選，隨後輸入物體類別，單張圖片多目標則重複操做，目標框選完成後，保存操做。瀏覽器

　　五、重複上述操做，直至全部圖片完成選定。app

【圖片標註數據處理】dom

　　一、打開xml_to_csv.py，修改path 爲對應train、test文件夾路徑，並運行，在對應目錄下將會生成csv文件,將生成的csv文件拷貝到models-master\research\object_detection\data文件夾下。ide

# -*- coding: utf-8 -*-
"""
Created on Sat Apr 14 10:01:27 2018

@author: Administrator
"""
# -*- coding: utf-8 -*-  
""" 
Created on Tue Jan 16 00:52:02 2018 
@author: Xiang Guo 
將文件夾內全部XML文件的信息記錄到CSV文件中 
"""  
  
import os  
import glob  
import pandas as pd  
import xml.etree.ElementTree as ET  

#XML文件路徑
pathStr='F:\\模型訓練\\img\\train';
  
os.chdir(pathStr)  
path = 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')[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('person.csv', index=None)  
    print('Successfully converted xml to csv.')  
  
  
main()

View Code

　　二、打開python generate_tfrecord.py，將對應的label改爲本身的類別，python generate_tfrecord.py --csv_input=data/person_train.csv --output_path=data/person_train.record，輸入對應train、test.csv文件路徑，生成對應tfrecord數據文件。post

# -*- coding: utf-8 -*-
"""
Created on Sat Apr 14 10:04:27 2018

@author: Administrator
"""

# -*- coding: utf-8 -*-  
""" 
由CSV文件生成TFRecord文件 
"""  
  
""" 
Usage: 
  # From tensorflow/models/ 
  # Create train data: 
  python csv_to_TFRecords.py --csv_input=data/train_labels.csv  --output_path=data/person_train.record 
  # Create test data: 
  python csv_to_TFRecords.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  
  
#這改爲object_detection路徑
os.chdir('F:\\模型訓練\\models-master\\research\\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 = flags.FLAGS  
  
  
# TO-DO replace this with label map  
#注意將對應的label改爲本身的類別！！！！！！！！！！  
def class_text_to_int(row_label):  
    if row_label == 'person':  
        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)  
    path = os.path.join(os.getcwd(), 'images')  
    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()

View Code

　　三、打開或下載ssd_mobilenet_v1_coco.config配置文件，修改訓練、測試數據路徑、分類數、批次圖片數量（避免超出顯存，稍微小點），放置在models-master\research\object_detection\training文件夾下。測試

# 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 {
  #訓練的數據類數
    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: {
  batch_size: 1#訓練批次
  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
    }
  }
  #這兩行註釋
  #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 {
    }
  }
}
#訓練數據
train_input_reader: {
  tf_record_input_reader {
    input_path: "data/person_train.record"
  }
  label_map_path: "data/person.pbtxt"
}

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
}
#測試數據
eval_input_reader: {
  tf_record_input_reader {
    input_path: "data/person_test.record"
  }
  label_map_path: "data/person.pbtxt"
  shuffle: false
  num_readers: 1
}

View Code

　　四、在data文件下建立對應.pbtxt文件，修改類型對應的ID序號，id序號注意與前面建立CSV文件時保持一致。

item {  
  id: 1  
  name: 'person'  
}  
  
item {  
  id: 2  
  name: 'car'  
}

【訓練模型】

　　一、在models-master\research\object_detection目錄下運行python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_coco.config

　　二、等待loss穩定在一個比較小的值之間，則能夠中止訓練。（直接關閉窗口以上便可）

　　三、可視化操做：在models-master\research\object_detection文件夾下，運行tensorboard --logdir='training' ，而後在瀏覽器中輸入localhost:6006便可查看模型訓練的各項參數狀況。

四、Anaconda Prompt 定位到 models\research\object_detection 文件夾下，運行

python export_inference_graph.py \ --input_type image_tensor \ --pipeline_config_path training/ssd_mobilenet_v1_coco.config \  --trained_checkpoint_prefix training/model.ckpt-31012 \  --output_directory person_vehicle_inference_graph

　　trained_checkpoint_prefix training/model.ckpt-31012 這個checkpoint（.ckpt-後面的數字）能夠在training文件夾下找到你本身訓練的模型的狀況，填上對應的數字（若是有多個，選最大的）。
　　output_directory tv_vehicle_inference_graph 改爲本身的名字

　　運行完後，能夠在person_vehicle_inference_graph （這是個人名字）文件夾下發現若干文件，有saved_model、checkpoint、frozen_inference_graph.pb等。 .pb結尾的就是最重要的frozen model了，還記得第一大部分中frozen model嗎？沒錯，就是咱們在後面要用到的部分

【測試模型】

　　一、打開jupyter notebook，先複製object detection API自帶的object_detection_tutorial.ipynb代碼；

　　二、將模型修改成剛剛導出的模型地址，以及pbtxt文件位置；

　　三、設置測試圖片路徑

　　四、運行

源碼獲取方式，關注公總號RaoRao1994，查看往期精彩-全部文章，，便可獲取資源下載連接

更多資源獲取，請關注公總號RaoRao1994