def test_return_non_default_batch_norm_params_keras_override( self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } batch_norm { decay: 0.7 center: false scale: true epsilon: 0.03 } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) self.assertTrue(keras_config.use_batch_norm()) batch_norm_params = keras_config.batch_norm_params(momentum=0.4) self.assertAlmostEqual(batch_norm_params['momentum'], 0.4) self.assertAlmostEqual(batch_norm_params['epsilon'], 0.03) self.assertFalse(batch_norm_params['center']) self.assertTrue(batch_norm_params['scale'])
def test_return_batch_norm_params_with_notrain_when_train_is_false(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } batch_norm { decay: 0.7 center: false scale: true epsilon: 0.03 train: false } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] self.assertEqual(conv_scope_arguments['normalizer_fn'], slim.batch_norm) batch_norm_params = scope[_get_scope_key(slim.batch_norm)] self.assertAlmostEqual(batch_norm_params['decay'], 0.7) self.assertAlmostEqual(batch_norm_params['epsilon'], 0.03) self.assertFalse(batch_norm_params['center']) self.assertTrue(batch_norm_params['scale']) self.assertFalse(batch_norm_params['is_training'])
def _build_arg_scope_with_conv_hyperparams(): conv_hyperparams = hyperparams_pb2.Hyperparams() conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } """ text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams) return hyperparams_builder.build(conv_hyperparams, is_training=True)
def _build_conv_hyperparams(): conv_hyperparams = hyperparams_pb2.Hyperparams() conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } """ text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams) return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def _build_arg_scope_with_hyperparams(op_type=hyperparams_pb2.Hyperparams.FC): hyperparams = hyperparams_pb2.Hyperparams() hyperparams_text_proto = """ activation: NONE regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } """ text_format.Merge(hyperparams_text_proto, hyperparams) hyperparams.op = op_type return hyperparams_builder.build(hyperparams, is_training=True)
def test_default_arg_scope_has_conv2d_transpose_op(self): conv_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() self.assertTrue(_get_scope_key(slim.conv2d_transpose) in scope)
def _build_conv_arg_scope_no_batch_norm(self): conv_hyperparams = hyperparams_pb2.Hyperparams() conv_hyperparams_text_proto = """ activation: RELU_6 regularizer { l2_regularizer { } } initializer { random_normal_initializer { stddev: 0.01 mean: 0.0 } } """ text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams) return hyperparams_builder.build(conv_hyperparams, is_training=True)
def _build_conv_hyperparams(): conv_hyperparams = hyperparams_pb2.Hyperparams() conv_hyperparams_text_proto = """ activation: RELU_6 regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } batch_norm { scale: false } """ text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams) return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def test_do_not_use_batch_norm_if_default(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] self.assertEqual(conv_scope_arguments['normalizer_fn'], None)
def test_explicit_fc_op_arg_scope_has_fully_connected_op(self): conv_hyperparams_text_proto = """ op: FC regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() self.assertTrue(_get_scope_key(slim.fully_connected) in scope)
def test_override_activation_keras(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } activation: RELU_6 """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) new_params = keras_config.params(activation=tf.nn.relu) self.assertEqual(new_params['activation'], tf.nn.relu)
def test_separable_conv2d_and_conv2d_and_transpose_have_same_parameters(self): conv_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() kwargs_1, kwargs_2, kwargs_3 = scope.values() self.assertDictEqual(kwargs_1, kwargs_2) self.assertDictEqual(kwargs_1, kwargs_3)
def test_use_relu_6_activation(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } activation: RELU_6 """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] self.assertEqual(conv_scope_arguments['activation_fn'], tf.nn.relu6)
def test_variance_in_range_with_random_normal_initializer_keras(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { random_normal_initializer { mean: 0.0 stddev: 0.8 } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) initializer = keras_config.params()['kernel_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=0.64, tol=1e-1)
def _build_conv_hyperparams(self): conv_hyperparams = hyperparams_pb2.Hyperparams() conv_hyperparams_text_proto = """ activation: RELU_6 regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } batch_norm { train: true, scale: false, center: true, decay: 0.2, epsilon: 0.1, } """ text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams) return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def test_return_l2_regularizer_weights_keras(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { weight: 0.42 } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) regularizer = keras_config.params()['kernel_regularizer'] weights = np.array([1., -1, 4., 2.]) with self.test_session() as sess: result = sess.run(regularizer(tf.constant(weights))) self.assertAllClose(np.power(weights, 2).sum() / 2.0 * 0.42, result)
def test_variance_in_range_with_random_normal_initializer(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { random_normal_initializer { mean: 0.0 stddev: 0.8 } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] initializer = conv_scope_arguments['weights_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=0.64, tol=1e-1)
def test_variance_in_range_with_variance_scaling_initializer_uniform_keras( self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { variance_scaling_initializer { factor: 2.0 mode: FAN_IN uniform: true } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) initializer = keras_config.params()['kernel_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=2. / 100.)
def test_do_not_use_batch_norm_if_default_keras(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) self.assertFalse(keras_config.use_batch_norm()) self.assertEqual(keras_config.batch_norm_params(), {}) # The batch norm builder should build an identity Lambda layer identity_layer = keras_config.build_batch_norm() self.assertTrue(isinstance(identity_layer, tf.keras.layers.Lambda))
def test_use_relu_6_activation_keras(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_normal_initializer { } } activation: RELU_6 """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) keras_config = hyperparams_builder.KerasLayerHyperparams( conv_hyperparams_proto) self.assertEqual(keras_config.params()['activation'], None) self.assertEqual( keras_config.params(include_activation=True)['activation'], tf.nn.relu6) activation_layer = keras_config.build_activation_layer() self.assertTrue(isinstance(activation_layer, tf.keras.layers.Lambda)) self.assertEqual(activation_layer.function, tf.nn.relu6)
def test_return_l1_regularized_weights(self): conv_hyperparams_text_proto = """ regularizer { l1_regularizer { weight: 0.5 } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = [v for v in scope.values()][0] regularizer = conv_scope_arguments['weights_regularizer'] weights = np.array([1., -1, 4., 2.]) with self.test_session() as sess: result = sess.run(regularizer(tf.constant(weights))) self.assertAllClose(np.abs(weights).sum() * 0.5, result)
def test_variance_in_range_with_variance_scaling_initializer_uniform(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { variance_scaling_initializer { factor: 2.0 mode: FAN_IN uniform: true } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] initializer = conv_scope_arguments['weights_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=2. / 100.)
def test_return_l2_regularizer_weights(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { weight: 0.42 } } initializer { truncated_normal_initializer { } } """ conv_hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto) scope_fn = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) scope = scope_fn() conv_scope_arguments = scope[_get_scope_key(slim.conv2d)] regularizer = conv_scope_arguments['weights_regularizer'] weights = np.array([1., -1, 4., 2.]) with self.test_session() as sess: result = sess.run(regularizer(tf.constant(weights))) self.assertAllClose(np.power(weights, 2).sum() / 2.0 * 0.42, result)