from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import logging
import tensorflow as tf
import tensorflow.contrib.layers as layers
import tensorflow.contrib.losses as losses
import tensorflow.contrib.slim as slim
from six.moves import range
from util import predictron_arg_scope
logging.basicConfig()
logger = logging.getLogger('predictron')
logger.setLevel(logging.INFO)
def iter_func(self, state):
sc = predictron_arg_scope()
with tf.variable_scope('value'):
value_net = slim.fully_connected(slim.flatten(state), 32, scope='fc0')
value_net = layers.batch_norm(value_net, activation_fn=tf.nn.relu, scope='fc0/preact')
value_net = slim.fully_connected(value_net, self.maze_size, activation_fn=None, scope='fc1')
with slim.arg_scope(sc):
net = slim.conv2d(state, 32, [3, 3], scope='conv1')
net = layers.batch_norm(net, activation_fn=tf.nn.relu, scope='conv1/preact')
net_flatten = slim.flatten(net, scope='conv1/flatten')
with tf.variable_scope('reward'):
reward_net = slim.fully_connected(net_flatten, 32, scope='fc0')
reward_net = layers.batch_norm(reward_net, activation_fn=tf.nn.relu, scope='fc0/preact')
reward_net = slim.fully_connected(reward_net, self.maze_size, activation_fn=None, scope='fc1')
with tf.variable_scope('gamma'):
gamma_net = slim.fully_connected(net_flatten, 32, scope='fc0')
gamma_net = layers.batch_norm(gamma_net, activation_fn=tf.nn.relu, scope='fc0/preact')
gamma_net = slim.fully_connected(gamma_net, self.maze_size, activation_fn=tf.nn.sigmoid, scope='fc1')
with tf.variable_scope('lambda'):
lambda_net = slim.fully_connected(net_flatten, 32, scope='fc0')
lambda_net = layers.batch_norm(lambda_net, activation_fn=tf.nn.relu, scope='fc0/preact')
lambda_net = slim.fully_connected(lambda_net, self.maze_size, activation_fn=tf.nn.sigmoid, scope='fc1')
net = slim.conv2d(net, 32, [3, 3], scope='conv2')
net = layers.batch_norm(net, activation_fn=tf.nn.relu, scope='conv2/preact')
net = slim.conv2d(net, 32, [3, 3], scope='conv3')
net = layers.batch_norm(net, activation_fn=tf.nn.relu, scope='conv3/preact')
return net, reward_net, gamma_net, lambda_net, value_net
所以我试图在tensorflow 2.0中对此进行编码,但是我有几个问题。
我对范围感到困惑。例如,我很困惑
with tf.variable_scope('reward'):
reward_net = slim.fully_connected(net_flatten, 32, scope='fc0')
reward_net = layers.batch_norm(reward_net, activation_fn=tf.nn.relu, scope='fc0/preact')
reward_net = slim.fully_connected(reward_net, self.maze_size, activation_fn=None, scope='fc1')
这是做什么的?我知道它会创建一个神经网络,但我在网上看不到任何能解释这种语法的东西。有人帮忙吗?