讀源碼google目標檢測

object_detection/core

定義各種class類，anchor_generator，box_coder，loss，detectionModel

object_detection/build

該文件夾目的是根據config參數build相應的class類的參數

object_detection/protos

定義配置參數的可選範圍

object_detection/meta_architectures/

對core中model.py的繼承，擴展，包含faster_rcnn，ssd，rfcn

object_detection/anchor_generator

對coreo中anchor_generator的繼承，擴展

object_detection/models

在meta_architectures網絡結構基礎上，對特徵提取繼承，擴展

train.py代碼

import functools
import json
import os
import tensorflow as tf

from object_detection import trainer
from object_detection.builders import dataset_builder
from object_detection.builders import model_builder
from object_detection.utils import config_util
from object_detection.utils import dataset_util
os.environ["CUDA_VISIBLE_DEVICES"] = '1'
tf.logging.set_verbosity(tf.logging.INFO)

flags = tf.app.flags
flags.DEFINE_string('master', '', 'Name of the TensorFlow master to use.')
flags.DEFINE_integer('task', 0, 'task id')
flags.DEFINE_integer('num_clones', 1, 'Number of clones to deploy per worker.')
flags.DEFINE_boolean('clone_on_cpu', False,
                     'Force clones to be deployed on CPU.  Note that even if '
                     'set to False (allowing ops to run on gpu), some ops may '
                     'still be run on the CPU if they have no GPU kernel.')
flags.DEFINE_integer('worker_replicas', 1, 'Number of worker+trainer '
                     'replicas.')
flags.DEFINE_integer('ps_tasks', 0,
                     'Number of parameter server tasks. If None, does not use '
                     'a parameter server.')
flags.DEFINE_string('train_dir', '/home/iris/Documents/model/test/train',
                    'Directory to save the checkpoints and training summaries.')

flags.DEFINE_string('pipeline_config_path', '/home/iris/Documents/configs/rfcn_resnet101_1class.config',
                    'Path to a pipeline_pb2.TrainEvalPipelineConfig config '
                    'file. If provided, other configs are ignored')


FLAGS = flags.FLAGS


def main(_):
#獲取config值
  assert FLAGS.train_dir, '`train_dir` is missing.'
  if FLAGS.task == 0: tf.gfile.MakeDirs(FLAGS.train_dir)
  if FLAGS.pipeline_config_path:
    configs = config_util.get_configs_from_pipeline_file(
        FLAGS.pipeline_config_path)
    #print(configs)
    if FLAGS.task == 0:
      tf.gfile.Copy(FLAGS.pipeline_config_path,
                    os.path.join(FLAGS.train_dir, 'pipeline.config'),
                    overwrite=True)

  model_config = configs['model']
  train_config = configs['train_config']
  input_config = configs['train_input_config']
#定義model參數
  model_fn = functools.partial(
      model_builder.build,
      model_config=model_config,
      is_training=True)

  def get_next(config):
    return dataset_util.make_initializable_iterator(
        dataset_builder.build(config)).get_next()

  create_input_dict_fn = functools.partial(get_next, input_config)
#是關於實現分佈式訓練的，一般都是單機訓練，沒有什麼卵用
  env = json.loads(os.environ.get('TF_CONFIG', '{}'))
  cluster_data = env.get('cluster', None)
  cluster = tf.train.ClusterSpec(cluster_data) if cluster_data else None
  task_data = env.get('task', None) or {'type': 'master', 'index': 0}
  task_info = type('TaskSpec', (object,), task_data)

  # Parameters for a single worker.
  ps_tasks = 0
  worker_replicas = 1
  worker_job_name = 'lonely_worker'
  task = 0
  is_chief = True
  master = ''

  if cluster_data and 'worker' in cluster_data:
    # Number of total worker replicas include "worker"s and the "master".
    worker_replicas = len(cluster_data['worker']) + 1
  if cluster_data and 'ps' in cluster_data:
    ps_tasks = len(cluster_data['ps'])

  if worker_replicas > 1 and ps_tasks < 1:
    raise ValueError('At least 1 ps task is needed for distributed training.')

  if worker_replicas >= 1 and ps_tasks > 0:
    print("Set up distributed training")
    # Set up distributed training.
    server = tf.train.Server(tf.train.ClusterSpec(cluster), protocol='grpc',
                             job_name=task_info.type,
                             task_index=task_info.index)
    if task_info.type == 'ps':
      server.join()
      return

    worker_job_name = '%s/task:%d' % (task_info.type, task_info.index)
    task = task_info.index
    is_chief = (task_info.type == 'master')
    master = server.target
#跳轉到trainer.py
  trainer.train(create_input_dict_fn, model_fn, train_config, master, task,
                FLAGS.num_clones, worker_replicas, FLAGS.clone_on_cpu, ps_tasks,
                worker_job_name, is_chief, FLAGS.train_dir)


if __name__ == '__main__':
  tf.app.run()

trainer.py

訓練函數，使用定義訓練方法是tf.contrib.slim