Python random_seed.set_random_seed方法代码示例

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testAtrousFullyConvolutionalValues(self):
    """Verify dense feature extraction with atrous convolution."""
    nominal_stride = 32
    for output_stride in [4, 8, 16, 32, None]:
      with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
        with ops.Graph().as_default():
          with self.test_session() as sess:
            random_seed.set_random_seed(0)
            inputs = create_test_input(2, 81, 81, 3)
            # Dense feature extraction followed by subsampling.
            output, _ = self._resnet_small(
                inputs, None, global_pool=False, output_stride=output_stride)
            if output_stride is None:
              factor = 1
            else:
              factor = nominal_stride // output_stride
            output = resnet_utils.subsample(output, factor)
            # Make the two networks use the same weights.
            variable_scope.get_variable_scope().reuse_variables()
            # Feature extraction at the nominal network rate.
            expected, _ = self._resnet_small(inputs, None, global_pool=False)
            sess.run(variables.global_variables_initializer())
            self.assertAllClose(
                output.eval(), expected.eval(), atol=1e-4, rtol=1e-4) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNoInitAssignCanAchieveZeroLoss(self):
    logdir = os.path.join(
        tempfile.mkdtemp(prefix=self.get_temp_dir()), 'tmp_logs')
    g = ops.Graph()
    with g.as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = BatchNormClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

      loss = learning.train(
          train_op, logdir, number_of_steps=300, log_every_n_steps=10)
      self.assertLess(loss, .1) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testUseGlobalStep(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = BatchNormClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()
      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

      global_step = variables_lib2.get_or_create_global_step()

      with session.Session() as sess:
        # Initialize all variables
        sess.run(variables_lib.global_variables_initializer())

        for _ in range(10):
          sess.run([train_op])
        global_step = global_step.eval()
        # After 10 updates global_step should be 10.
        self.assertAllClose(global_step, 10) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testNoneGlobalStep(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = BatchNormClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()
      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(
          total_loss, optimizer, global_step=None)

      global_step = variables_lib2.get_or_create_global_step()

      with session.Session() as sess:
        # Initialize all variables
        sess.run(variables_lib.global_variables_initializer())

        for _ in range(10):
          sess.run([train_op])
        global_step = global_step.eval()
        # Since train_op don't use global_step it shouldn't change.
        self.assertAllClose(global_step, 0) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNonDefaultGraph(self):
    logdir = os.path.join(
        tempfile.mkdtemp(prefix=self.get_temp_dir()), 'tmp_logs')
    g = ops.Graph()
    with g.as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = LogisticClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

    loss = learning.train(
        train_op, logdir, number_of_steps=300, log_every_n_steps=10, graph=g)
    self.assertIsNotNone(loss)
    self.assertLess(loss, .015) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithSessionConfig(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = LogisticClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

      session_config = config_pb2.ConfigProto(allow_soft_placement=True)
      loss = learning.train(
          train_op,
          None,
          number_of_steps=300,
          log_every_n_steps=10,
          session_config=session_config)
    self.assertIsNotNone(loss)
    self.assertLess(loss, .015) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNoneAsLogdirWhenUsingSummariesRaisesError(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = LogisticClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()
      summary.scalar('total_loss', total_loss)

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)
      summary_op = summary.merge_all()

      with self.assertRaises(ValueError):
        learning.train(
            train_op, None, number_of_steps=300, summary_op=summary_op) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNoneAsLogdirWhenUsingTraceRaisesError(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = LogisticClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

      with self.assertRaises(ValueError):
        learning.train(
            train_op, None, number_of_steps=300, trace_every_n_steps=10) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNoneAsLogdirWhenUsingSaverRaisesError(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = LogisticClassifier(tf_inputs)
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)
      saver = saver_lib.Saver()

      with self.assertRaises(ValueError):
        learning.train(
            train_op, None, init_op=None, number_of_steps=300, saver=saver) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithLocalVariable(self):
    logdir = os.path.join(
        tempfile.mkdtemp(prefix=self.get_temp_dir()), 'tmp_logs')
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      local_multiplier = variables_lib2.local_variable(1.0)

      tf_predictions = LogisticClassifier(tf_inputs) * local_multiplier
      loss_ops.log_loss(tf_predictions, tf_labels)
      total_loss = loss_ops.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = learning.create_train_op(total_loss, optimizer)

      loss = learning.train(
          train_op, logdir, number_of_steps=300, log_every_n_steps=10)
      self.assertIsNotNone(loss)
      self.assertLess(loss, .015) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testGlobalStepIsIncrementedByDefault(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = batchnorm_classifier(tf_inputs)
      loss = losses.log_loss(tf_labels, tf_predictions)
      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)
      train_op = training.create_train_op(loss, optimizer)

      global_step = variables_lib.get_or_create_global_step()

      with self.cached_session() as session:
        # Initialize all variables
        session.run(variables_lib2.global_variables_initializer())

        for _ in range(10):
          session.run(train_op)

        # After 10 updates global_step should be 10.
        self.assertAllClose(global_step.eval(), 10) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testGlobalStepNotIncrementedWhenSetToNone(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = batchnorm_classifier(tf_inputs)
      loss = losses.log_loss(tf_labels, tf_predictions)
      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)
      train_op = training.create_train_op(loss, optimizer, global_step=None)

      global_step = variables_lib.get_or_create_global_step()

      with self.cached_session() as session:
        # Initialize all variables
        session.run(variables_lib2.global_variables_initializer())

        for _ in range(10):
          session.run(train_op)

        # Since train_op don't use global_step it shouldn't change.
        self.assertAllClose(global_step.eval(), 0) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithNoInitAssignCanAchieveZeroLoss(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      tf_predictions = batchnorm_classifier(tf_inputs)
      losses.log_loss(tf_labels, tf_predictions)
      total_loss = losses.get_total_loss()

      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)

      train_op = training.create_train_op(total_loss, optimizer)

      loss = training.train(
          train_op,
          None,
          hooks=[basic_session_run_hooks.StopAtStepHook(num_steps=300)],
          save_summaries_steps=None,
          save_checkpoint_secs=None)
      self.assertLess(loss, .1) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testTrainWithLocalVariable(self):
    with ops.Graph().as_default():
      random_seed.set_random_seed(0)
      tf_inputs = constant_op.constant(self._inputs, dtype=dtypes.float32)
      tf_labels = constant_op.constant(self._labels, dtype=dtypes.float32)

      local_multiplier = variables_lib.local_variable(1.0)

      tf_predictions = logistic_classifier(tf_inputs) * local_multiplier
      losses.log_loss(tf_labels, tf_predictions)
      total_loss = losses.get_total_loss()
      optimizer = gradient_descent.GradientDescentOptimizer(learning_rate=1.0)
      train_op = training.create_train_op(total_loss, optimizer)

      loss = training.train(
          train_op,
          None,
          hooks=[basic_session_run_hooks.StopAtStepHook(num_steps=300)],
          save_summaries_steps=None,
          save_checkpoint_secs=None)
      self.assertIsNotNone(loss)
      self.assertLess(loss, .015) 

# 需要导入模块: from tensorflow.python.framework import random_seed [as 别名]
# 或者: from tensorflow.python.framework.random_seed import set_random_seed [as 别名]
def testGradientNoise(self):
    random_seed.set_random_seed(42)
    with self.cached_session() as session:
      x, var, loss, global_step = _setup_model()
      train = optimizers_lib.optimize_loss(
          loss,
          global_step,
          learning_rate=0.1,
          optimizer="SGD",
          gradient_noise_scale=10.0)
      variables.global_variables_initializer().run()
      session.run(train, feed_dict={x: 5})
      var_value, global_step_value = session.run([var, global_step])
      # Due to randomness the following number may change if graph is different.
      self.assertAlmostEqual(var_value, 9.801016, 4)
      self.assertEqual(global_step_value, 1)