def testCustomNoiseShape(self): inputs = tf.ones((5, 3, 2)) noise_shape = [5, 1, 2] dp = core_layers.Dropout(0.5, noise_shape=noise_shape, seed=1) dropped = dp(inputs, training=True) self.evaluate(tf.compat.v1.global_variables_initializer()) np_output = self.evaluate(dropped) self.assertAlmostEqual(0., np_output.min()) self.assertAllClose(np_output[:, 0, :], np_output[:, 1, :])
def testDynamicRate(self):
with self.cached_session() as sess:
rate = tf.compat.v1.placeholder(dtype='float32', name='rate')
dp = core_layers.Dropout(rate, name='dropout')
inputs = tf.ones((5, 5))
dropped = dp(inputs, training=True)
self.evaluate(tf.compat.v1.global_variables_initializer())
np_output = sess.run(dropped, feed_dict={rate: 0.5})
self.assertAlmostEqual(0., np_output.min())
np_output = sess.run(dropped, feed_dict={rate: 0.0})
self.assertAllClose(np.ones((5, 5)), np_output)
def testBooleanLearningPhase(self):
dp = core_layers.Dropout(0.5)
inputs = tf.ones((5, 3))
dropped = dp(inputs, training=True)
if not tf.executing_eagerly():
self.evaluate(tf.compat.v1.global_variables_initializer())
np_output = self.evaluate(dropped)
self.assertAlmostEqual(0., np_output.min())
dropped = dp(inputs, training=False)
np_output = self.evaluate(dropped)
self.assertAllClose(np.ones((5, 3)), np_output)
def testDynamicLearningPhase(self):
with self.cached_session() as sess:
dp = core_layers.Dropout(0.5, seed=1)
inputs = tf.ones((5, 5))
training = tf.compat.v1.placeholder(dtype='bool')
dropped = dp(inputs, training=training)
self.evaluate(tf.compat.v1.global_variables_initializer())
np_output = sess.run(dropped, feed_dict={training: True})
self.assertAlmostEqual(0., np_output.min())
np_output = sess.run(dropped, feed_dict={training: False})
self.assertAllClose(np.ones((5, 5)), np_output)
def testDropoutProperties(self): dp = core_layers.Dropout(0.5, name='dropout') self.assertEqual(dp.rate, 0.5) self.assertEqual(dp.noise_shape, None) dp(tf.ones(())) self.assertEqual(dp.name, 'dropout')
