使用tf.layers时可替代arg_scope

问题描述

我正在使用tf.layers重写tf.contrib.slim.nets.inception_v3.不幸的是，新的tf.layers模块不能与arg_scope一起使用，因为它没有必要的装饰器.是否有更好的机制可以用来设置图层的默认参数?还是我应该在每个图层上添加适当的参数并删除arg_scope?

I'm rewriting tf.contrib.slim.nets.inception_v3 using tf.layers. Unfortunately the new tf.layers module does not work with arg_scope, as it does not have the necessary decorators. Is there better mechanism in place that I should use to set default paramters for layers? Or should I simply add a proper arguments to each layer and remove the arg_scope?

以下是使用arg_scope的示例:

Here is an example that uses the arg_scope:

with variable_scope.variable_scope(scope, 'InceptionV3', [inputs]):
    with arg_scope(
        [layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
        stride=1,
        padding='VALID'):

推荐答案

没有其他机制可以让您在核心TensorFlow中定义默认值，因此您应该为每个图层指定参数.

There isn't another mechanism that lets you define default values in core TensorFlow, so you should specify the arguments for each layer.

例如，此代码:

with slim.arg_scope([slim.fully_connected], 
    activation_fn=tf.nn.relu, 
    weights_initializer=tf.truncated_normal_initializer(stddev=0.01),
    weights_regularizer=tf.contrib.layers.l2_regularizer(scale=0.0005)):
  x = slim.fully_connected(x, 800)
  x = slim.fully_connected(x, 1000)

将成为:

x = tf.layers.dense(x, 800, activation=tf.nn.relu,
      kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
      kernel_regularizer=tf.contrib.layers.l2_regularizer(scale=0.0005))
x = tf.layers.dense(x, 1000, activation=tf.nn.relu,
      kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
      kernel_regularizer=tf.contrib.layers.l2_regularizer(scale=0.0005))

或者:

with tf.variable_scope('fc', 
    initializer=tf.truncated_normal_initializer(stddev=0.01)):
  x = tf.layers.dense(x, 800, activation=tf.nn.relu,
      kernel_regularizer=tf.contrib.layers.l2_regularizer(scale=0.0005))
  x = tf.layers.dense(x, 1000, activation=tf.nn.relu,
      kernel_regularizer=tf.contrib.layers.l2_regularizer(scale=0.0005))

请务必阅读该层的文档，以了解哪些初始化程序默认为变量作用域初始化程序.例如，密集层的kernel_initializer使用变量作用域初始化程序，而bias_initializer使用tf.zeros_initializer().

Make sure to read the documentation of the layer to see which initializers default to the variable scope initializer. For example, the dense layer's kernel_initializer uses the variable scope initializer, while the bias_initializer uses tf.zeros_initializer().

这篇关于使用tf.layers时可替代arg_scope的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！