当前位置: 首页>>代码示例>>Python>>正文


Python losses.l1_l2_regularizer方法代码示例

本文整理汇总了Python中inception.slim.losses.l1_l2_regularizer方法的典型用法代码示例。如果您正苦于以下问题:Python losses.l1_l2_regularizer方法的具体用法?Python losses.l1_l2_regularizer怎么用?Python losses.l1_l2_regularizer使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在inception.slim.losses的用法示例。


在下文中一共展示了losses.l1_l2_regularizer方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: testL1L2Regularizer

# 需要导入模块: from inception.slim import losses [as 别名]
# 或者: from inception.slim.losses import l1_l2_regularizer [as 别名]
def testL1L2Regularizer(self):
    with self.test_session():
      shape = [5, 5, 5]
      num_elem = 5 * 5 * 5
      tensor = tf.constant(1.0, shape=shape)
      loss = losses.l1_l2_regularizer()(tensor)
      self.assertEquals(loss.op.name, 'L1L2Regularizer/value')
      self.assertAlmostEqual(loss.eval(), num_elem + num_elem / 2, 5) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:10,代码来源:losses_test.py

示例2: testL1L2RegularizerWithScope

# 需要导入模块: from inception.slim import losses [as 别名]
# 或者: from inception.slim.losses import l1_l2_regularizer [as 别名]
def testL1L2RegularizerWithScope(self):
    with self.test_session():
      shape = [5, 5, 5]
      num_elem = 5 * 5 * 5
      tensor = tf.constant(1.0, shape=shape)
      loss = losses.l1_l2_regularizer(scope='L1L2')(tensor)
      self.assertEquals(loss.op.name, 'L1L2/value')
      self.assertAlmostEqual(loss.eval(), num_elem + num_elem / 2, 5) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:10,代码来源:losses_test.py

示例3: testL1L2RegularizerWithWeights

# 需要导入模块: from inception.slim import losses [as 别名]
# 或者: from inception.slim.losses import l1_l2_regularizer [as 别名]
def testL1L2RegularizerWithWeights(self):
    with self.test_session():
      shape = [5, 5, 5]
      num_elem = 5 * 5 * 5
      tensor = tf.constant(1.0, shape=shape)
      weight_l1 = 0.01
      weight_l2 = 0.05
      loss = losses.l1_l2_regularizer(weight_l1, weight_l2)(tensor)
      self.assertEquals(loss.op.name, 'L1L2Regularizer/value')
      self.assertAlmostEqual(loss.eval(),
                             num_elem * weight_l1 + num_elem * weight_l2 / 2, 5) 
开发者ID:ringringyi,项目名称:DOTA_models,代码行数:13,代码来源:losses_test.py


注:本文中的inception.slim.losses.l1_l2_regularizer方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。