tensorflow object detection api训练自己的模型

api的安装过程参考其他博客:

1. 制作数据集

1.1 数据标注

• 使用数据标注软件 labelImg 进行标注
• 得到csv格式数据集

1.2 生成tfrecord类型数据

将csvData文件夹复制进 object_detection/data 路径
在此路径下创建脚本 generate_tfrecord.py

# generate_tfrecord.py
# -*- coding: utf-8 -*-
"""
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('/home/mingjie/tf_model/models/research/object_detection/data')  #修改为自己的路径

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
def class_text_to_int(row_label):
    if row_label == 'car':     # 修改为自己的类别
        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(), 'CsvFile/images')         #  需改动
    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()

• 19行修改为自己的 object_detection/data 路径
• 27行按自己的类别修改

生成训练集文件

python generate_tfrecord.py --csv_input=../object_detection/data/CsvFile/train.csv --output_path=train.record

生成验证集文件

 python generate_tfrecord.py --csv_input=../object_detection/data/CsvFile//test.csv --output_path=test.record

成功运行的话,在data路径下会生成 train.record 和test.record两个文件

2. 训练

2.1 修改配置文件

在 object_detection/samples/configs 路径下找到对应网络的config文件
以 ssd-mobilenet-v2 为例,对应文件为ssd_mobilenet_v2_coco.config

2.2 训练

打开终端,在object detection路径下输入:

python3 model_main.py \
    --pipeline_config_path=training/ssd_mobilenet_v2_coco.config \
    --model_dir=training \
    --num_train_steps=150000 \
    --num_eval_steps=100 \
    --alsologtostderr

即开始训练
在训练过程中,每隔一轮会保存ckpt文件于training文件夹,直至达到训练次数或手动停止

2.3 查看训练情况

tensorboard能够将训练过程可视化,以此查看训练情况(及时止损)

tensorboard --logdir=training

在浏览器输入地址 http://localhost:6006/ (终端会输出一个网址,将其复制到浏览器地址栏)

• train loss 不断下降，test loss不断下降，说明网络仍在学习;
• train loss 不断下降，test loss趋于不变，说明网络过拟合;
• train loss 趋于不变，test loss不断下降，说明数据集100%有问题;
• train loss 趋于不变，test loss趋于不变，说明学习遇到瓶颈，需要减小学习率或批量数目;
• train loss 不断上升，test loss不断上升，说明网络结构设计不当，训练超参数设置不当，数据集经过清洗等问题。

3. 生成pb与pbtxt文件供opencv调用

3.1 生成pb文件

打开终端, 进入 object_detection 路径

python3 export_inference_graph.py --input_type image_tensor --pipeline_config_path training/ssd_mobilenet_v2_coco.config --trained_checkpoint_prefix training/model.ckpt-7988 --output_directory trained_model

输入参数:

• --pipeline_config_path:训练时所用的config文件
• --trained_checkpoint_prefix: 指定训练次数的model.ckpt
• --output_directory trained_model: 输出pb文件到此路径下

3.2 生成pbtxt文件

以 ssd-mobilenet-v2 为例,需要用到 opencv/samples/dnn 路径下的tf_graph_ssd.py脚本

python /home/mingjie/pmj_softwares/opencv-4.3.0/samples/dnn/tf_text_graph_ssd.py --input=./trained_model/frozen_inference_graph.pb --output=./trained_model/v2.pbtxt --config=./training/ssd_mobilenet_v2_coco.config

将opencv路径按自己环境修改