#coding=utf-8

# Copyright 2018 The TensorFlow Authors All Rights Reserved.

#

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

#

# http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

# ==============================================================================

"""Training script for the DeepLab model.

See model.py for more details and usage.

"""

import six

import tensorflow as tf

from deeplab import common

from deeplab import model

from deeplab.datasets import segmentation_dataset

from deeplab.utils import input_generator

from deeplab.utils import train_utils

from deployment import model_deploy

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #Log输出,'2'是只显示 warning 和 Error

slim = tf.contrib.slim #“代码瘦身”，简化版的tf

prefetch_queue = slim.prefetch_queue #读取数据的代码，使用预加载队列

flags = tf.app.flags #相当于python中的argparse，处理sys.argv的输出

#用于支持接受命令行传递参数，相当于接受argv。

FLAGS = flags.FLAGS

#第一个是参数名称，第二个参数是默认值，第三个是参数描述

# Settings for multi-GPUs/multi-replicas training.

#GPU等训练设置

flags.DEFINE_integer('num_clones', 1, 'Number of clones to deploy.')

flags.DEFINE_boolean('clone_on_cpu', False, 'Use CPUs to deploy clones.')

flags.DEFINE_integer('num_replicas', 1, 'Number of worker replicas.')

flags.DEFINE_integer('startup_delay_steps', 15,

'Number of training steps between replicas startup.')

flags.DEFINE_integer('num_ps_tasks', 0,

'The number of parameter servers. If the value is 0, then '

'the parameters are handled locally by the worker.')

flags.DEFINE_string('master', '', 'BNS name of the tensorflow server')

flags.DEFINE_integer('task', 0, 'The task ID.')

flags.DEFINE_string('model_variant', "xception_65",

'DeepLab model variant.')

# Settings for logging.

#日志设置

flags.DEFINE_string('train_logdir', '/home/cxx/Deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train',

'Where the checkpoint and logs are stored.')

flags.DEFINE_integer('log_steps', 10,

'Display logging information at every log_steps.')

flags.DEFINE_integer('save_interval_secs', 1200,

'How often, in seconds, we save the model to disk.')

flags.DEFINE_integer('save_summaries_secs', 600,

'How often, in seconds, we compute the summaries.')

flags.DEFINE_boolean('save_summaries_images', False,

'Save sample inputs, labels, and semantic predictions as '

'images to summary.')

# Settings for training strategy.

#训练策略设置

flags.DEFINE_enum('learning_policy', 'poly', ['poly', 'step'],

'Learning rate policy for training.') #name, default, enum_values, help;poly-多元

# Use 0.007 when training on PASCAL augmented training set, train_aug. When

# fine-tuning on PASCAL trainval set, use learning rate=0.0001.

#学习率

flags.DEFINE_float('base_learning_rate', .0001,

'The base learning rate for model training.')

#学习率衰减

flags.DEFINE_float('learning_rate_decay_factor', 0.1,

'The rate to decay the base learning rate.')

#每2000衰减一次

flags.DEFINE_integer('learning_rate_decay_step', 2000,

'Decay the base learning rate at a fixed step.')

#

flags.DEFINE_float('learning_power', 0.9,

'The power value used in the poly learning policy.')

#训练迭代次数

flags.DEFINE_integer('training_number_of_steps', 1000,

'The number of steps used for training')

#动量

flags.DEFINE_float('momentum', 0.9, 'The momentum value to use')

# When fine_tune_batch_norm=True, use at least batch size larger than 12

# (batch size more than 16 is better). Otherwise, one could use smaller batch

# size and set fine_tune_batch_norm=False.

#训练的batchsize

flags.DEFINE_integer('train_batch_size', 1,

'The number of images in each batch during training.')

# For weight_decay, use 0.00004 for MobileNet-V2 or Xcpetion model variants.

# Use 0.0001 for ResNet model variants.

flags.DEFINE_float('weight_decay', 0.00004,

'The value of the weight decay for training.')

#训练图片的裁剪大小

flags.DEFINE_multi_integer('train_crop_size', [513, 513],

'Image crop size [height, width] during training.')

#

flags.DEFINE_float('last_layer_gradient_multiplier', 1.0,

'The gradient multiplier for last layers, which is used to '

'boost the gradient of last layers if the value > 1.')

flags.DEFINE_boolean('upsample_logits', True,

'Upsample logits during training.')

# Settings for fine-tuning the network.

#预训练的初始checkpoint，如果有就用，指明文件如～/model.ckpt

flags.DEFINE_string('tf_initial_checkpoint', '/home/cxx/Deeplab/models/research/deeplab/backbone/deeplabv3_cityscapes_train/model.ckpt',

'The initial checkpoint in tensorflow format.')

# Set to False if one does not want to re-use the trained classifier weights.

#想不想重复利用以训练好的分类器权重

flags.DEFINE_boolean('initialize_last_layer', True,

'Initialize the last layer.')

flags.DEFINE_boolean('last_layers_contain_logits_only', False,

'Only consider logits as last layers or not.')

flags.DEFINE_integer('slow_start_step', 0,

'Training model with small learning rate for few steps.')

flags.DEFINE_float('slow_start_learning_rate', 1e-4,

'Learning rate employed during slow start.')

# Set to True if one wants to fine-tune the batch norm parameters in DeepLabv3.

# Set to False and use small batch size to save GPU memory.

#True-微调batch的参数

#False-使用小的batch size

flags.DEFINE_boolean('fine_tune_batch_norm', True,

'Fine tune the batch norm parameters or not.')

flags.DEFINE_float('min_scale_factor', 0.5,

'Mininum scale factor for data augmentation.')

flags.DEFINE_float('max_scale_factor', 2.,

'Maximum scale factor for data augmentation.')

flags.DEFINE_float('scale_factor_step_size', 0.25,

'Scale factor step size for data augmentation.')

# For `xception_65`, use atrous_rates = [12, 24, 36] if output_stride = 8, or

# rates = [6, 12, 18] if output_stride = 16. For `mobilenet_v2`, use None. Note

# one could use different atrous_rates/output_stride during training/evaluation.

# 空洞卷积的参数

flags.DEFINE_multi_integer('atrous_rates', [6,12,18],

'Atrous rates for atrous spatial pyramid pooling.')

#输入与输出的空间分辨率之比

flags.DEFINE_integer('output_stride', 16,

'The ratio of input to output spatial resolution.')

# Dataset settings.

# 数据集

flags.DEFINE_string('dataset', "cityscapes",

'Name of the segmentation dataset.')

flags.DEFINE_string('train_split', 'train',

'Which split of the dataset to be used for training')

# 数据集地址

flags.DEFINE_string('dataset_dir', '/home/cxx/Deeplab/models/research/deeplab/datasets/cityscapes/tfrecord', 'Where the dataset reside.')

def _build_deeplab(inputs_queue, outputs_to_num_classes, ignore_label):

return outputs_to_scales_to_logits

def main(unused_argv):

save_interval_secs=FLAGS.save_interval_secs)

if __name__ == '__main__':

'''

training_number_of_steps = 1000

train_split = "train"

model_variant = "xception_65"

atrous_rates = 6

atrous_rates = 12

atrous_rates = 18

output_stride = 16

decoder_output_stride = 4

train_crop_size = 513

train_crop_size = 513

train_batch_size = 1

dataset = "cityscapes"

tf_initial_checkpoint = '/home/cxx/Deeplab/models/research/deeplab/backbone/deeplabv3_cityscapes_train/model.ckpt'

train_logdir = '/home/cxx/Deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train'

dataset_dir = '/home/cxx/Deeplab/models/research/deeplab/datasets/cityscapes/tfrecord'

'''

tf.app.run()