Python losses.maximum_mean_discrepancy() Examples

The following are 30 code examples of losses.maximum_mean_discrepancy(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module losses , or try the search function .
Example #1
Source File: losses_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #2
Source File: losses_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #3
Source File: losses_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #4
Source File: losses_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #5
Source File: losses_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)
Example #6
Source File: losses_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def test_mmd_name(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      loss = losses.maximum_mean_discrepancy(x, x, kernel)

      self.assertEquals(loss.op.name, 'MaximumMeanDiscrepancy/value')
Example #7
Source File: losses_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #8
Source File: losses_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #9
Source File: losses_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #10
Source File: losses_test.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)
Example #11
Source File: losses_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_name(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      loss = losses.maximum_mean_discrepancy(x, x, kernel)

      self.assertEquals(loss.op.name, 'MaximumMeanDiscrepancy/value')
Example #12
Source File: losses_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #13
Source File: losses_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #14
Source File: losses_test.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_name(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      loss = losses.maximum_mean_discrepancy(x, x, kernel)

      self.assertEquals(loss.op.name, 'MaximumMeanDiscrepancy/value')
Example #15
Source File: losses_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)
Example #16
Source File: losses_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_name(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      loss = losses.maximum_mean_discrepancy(x, x, kernel)

      self.assertEquals(loss.op.name, 'MaximumMeanDiscrepancy/value')
Example #17
Source File: losses_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #18
Source File: losses_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #19
Source File: losses_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #20
Source File: losses_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)
Example #21
Source File: losses_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_name(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      loss = losses.maximum_mean_discrepancy(x, x, kernel)

      self.assertEquals(loss.op.name, 'MaximumMeanDiscrepancy/value')
Example #22
Source File: losses_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #23
Source File: losses_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #24
Source File: losses_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #25
Source File: losses_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)
Example #26
Source File: losses_test.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #27
Source File: losses_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_inputs_are_same(self):
    with self.test_session():
      x = tf.random_uniform((2, 3), seed=1)
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      self.assertEquals(0, losses.maximum_mean_discrepancy(x, x, kernel).eval())
Example #28
Source File: losses_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def test_fast_mmd_is_similar_to_slow_mmd(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      cost_old = MaximumMeanDiscrepancySlow(x, y, [1.]).eval()
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([1.]))
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #29
Source File: losses_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def test_multiple_sigmas(self):
    with self.test_session():
      x = tf.constant(np.random.normal(size=(2, 3)), tf.float32)
      y = tf.constant(np.random.rand(2, 3), tf.float32)

      sigmas = tf.constant([2., 5., 10, 20, 30])
      kernel = partial(utils.gaussian_kernel_matrix, sigmas=sigmas)
      cost_old = MaximumMeanDiscrepancySlow(x, y, [2., 5., 10, 20, 30]).eval()
      cost_new = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(cost_old, cost_new, delta=1e-5)
Example #30
Source File: losses_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def test_mmd_is_zero_when_distributions_are_same(self):

    with self.test_session():
      x = tf.random_uniform((1000, 10), seed=1)
      y = tf.random_uniform((1000, 10), seed=3)

      kernel = partial(utils.gaussian_kernel_matrix, sigmas=tf.constant([100.]))
      loss = losses.maximum_mean_discrepancy(x, y, kernel=kernel).eval()

      self.assertAlmostEqual(0, loss, delta=1e-4)