def test_default_rfcn_box_predictor(self): conv_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } activation: RELU_6 """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, hyperparams_proto) def mock_conv_argscope_builder(conv_hyperparams_arg, is_training): return (conv_hyperparams_arg, is_training) box_predictor_proto = box_predictor_pb2.BoxPredictor() box_predictor_proto.rfcn_box_predictor.conv_hyperparams.CopyFrom( hyperparams_proto) box_predictor = box_predictor_builder.build( argscope_fn=mock_conv_argscope_builder, box_predictor_config=box_predictor_proto, is_training=True, num_classes=90) self.assertEqual(box_predictor.num_classes, 90) self.assertTrue(box_predictor._is_training) self.assertEqual(box_predictor._box_code_size, 4) self.assertEqual(box_predictor._num_spatial_bins, [3, 3]) self.assertEqual(box_predictor._crop_size, [12, 12])
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = scope.values()[0] self.assertEqual(conv_scope_arguments['normalizer_fn'], slim.batch_norm) batch_norm_params = conv_scope_arguments['normalizer_params'] 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 test_box_predictor_builder_calls_fc_argscope_fn(self): fc_hyperparams_text_proto = """ regularizer { l1_regularizer { weight: 0.0003 } } initializer { truncated_normal_initializer { mean: 0.0 stddev: 0.3 } } activation: RELU_6 op: FC """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(fc_hyperparams_text_proto, hyperparams_proto) box_predictor_proto = box_predictor_pb2.BoxPredictor() box_predictor_proto.mask_rcnn_box_predictor.fc_hyperparams.CopyFrom( hyperparams_proto) mock_argscope_fn = mock.Mock(return_value='arg_scope') box_predictor = box_predictor_builder.build( argscope_fn=mock_argscope_fn, box_predictor_config=box_predictor_proto, is_training=False, num_classes=10) mock_argscope_fn.assert_called_with(hyperparams_proto, False) self.assertEqual(box_predictor._fc_hyperparams, 'arg_scope')
def _build_arg_scope_with_conv_hyperparams(self): 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 test_project_images(self): hyperparams = hyperparams_pb2.Hyperparams() text_format.Merge( r""" op: CONV activation: NONE regularizer { l2_regularizer { weight: 1e-8 } } initializer { truncated_normal_initializer { mean: 0.0 stddev: 0.03 } } batch_norm { decay: 0.995 center: true scale: false epsilon: 0.001 } """, hyperparams) model_proto = gap_model_pb2.GAPModel() model = gap_model.Model(model_proto, is_training=False) # Project to 50-D feature space. tf.reset_default_graph() inputs = tf.random_uniform(shape=[32, 7, 7, 320]) feature_map = model._project_images(inputs, common_dimensions=50, hyperparams=hyperparams, is_training=False) self.assertAllEqual(feature_map.get_shape().as_list(), [32, 7, 7, 50]) # Project to 199-D feature space. tf.reset_default_graph() inputs = tf.random_uniform(shape=[32, 14, 14, 320]) feature_map = model._project_images(inputs, common_dimensions=199, hyperparams=hyperparams, is_training=False) self.assertAllEqual(feature_map.get_shape().as_list(), [32, 14, 14, 199])
def test_construct_non_default_conv_box_predictor(self): box_predictor_text_proto = """ convolutional_box_predictor { min_depth: 2 max_depth: 16 num_layers_before_predictor: 2 use_dropout: false dropout_keep_probability: 0.4 kernel_size: 3 box_code_size: 3 apply_sigmoid_to_scores: true class_prediction_bias_init: 4.0 use_depthwise: true } """ conv_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, hyperparams_proto) def mock_conv_argscope_builder(conv_hyperparams_arg, is_training): return (conv_hyperparams_arg, is_training) box_predictor_proto = box_predictor_pb2.BoxPredictor() text_format.Merge(box_predictor_text_proto, box_predictor_proto) box_predictor_proto.convolutional_box_predictor.conv_hyperparams.CopyFrom( hyperparams_proto) box_predictor = box_predictor_builder.build( argscope_fn=mock_conv_argscope_builder, box_predictor_config=box_predictor_proto, is_training=False, num_classes=10) self.assertEqual(box_predictor._min_depth, 2) self.assertEqual(box_predictor._max_depth, 16) self.assertEqual(box_predictor._num_layers_before_predictor, 2) self.assertFalse(box_predictor._use_dropout) self.assertAlmostEqual(box_predictor._dropout_keep_prob, 0.4) self.assertTrue(box_predictor._apply_sigmoid_to_scores) self.assertAlmostEqual(box_predictor._class_prediction_bias_init, 4.0) self.assertEqual(box_predictor.num_classes, 10) self.assertFalse(box_predictor._is_training) self.assertTrue(box_predictor._use_depthwise)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) self.assertTrue(self._get_scope_key(slim.conv2d_transpose) in scope)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) self.assertTrue(self._get_scope_key(slim.fully_connected) in scope)
def _build_arg_scope_with_hyperparams( self, 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_box_predictor_calls_fc_argscope_fn(self): conv_hyperparams_text_proto = """ regularizer { l1_regularizer { weight: 0.0003 } } initializer { truncated_normal_initializer { mean: 0.0 stddev: 0.3 } } activation: RELU_6 """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, hyperparams_proto) def mock_conv_argscope_builder(conv_hyperparams_arg, is_training): return (conv_hyperparams_arg, is_training) box_predictor_proto = box_predictor_pb2.BoxPredictor() box_predictor_proto.rfcn_box_predictor.conv_hyperparams.CopyFrom( hyperparams_proto) box_predictor = box_predictor_builder.build( argscope_fn=mock_conv_argscope_builder, box_predictor_config=box_predictor_proto, is_training=False, num_classes=10) (conv_hyperparams_actual, is_training) = box_predictor._conv_hyperparams self.assertAlmostEqual( (hyperparams_proto.regularizer.l1_regularizer.weight), (conv_hyperparams_actual.regularizer.l1_regularizer.weight)) self.assertAlmostEqual(( hyperparams_proto.initializer.truncated_normal_initializer.stddev), (conv_hyperparams_actual.initializer. truncated_normal_initializer.stddev)) self.assertAlmostEqual( (hyperparams_proto.initializer.truncated_normal_initializer.mean), (conv_hyperparams_actual.initializer.truncated_normal_initializer. mean)) self.assertEqual(hyperparams_proto.activation, conv_hyperparams_actual.activation) self.assertFalse(is_training)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = scope.values()[0] self.assertEqual(conv_scope_arguments['activation_fn'], tf.nn.relu6)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = scope.values()[0] self.assertEqual(conv_scope_arguments['normalizer_fn'], None) self.assertEqual(conv_scope_arguments['normalizer_params'], None)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) kwargs_1, kwargs_2, kwargs_3 = scope.values() self.assertDictEqual(kwargs_1, kwargs_2) self.assertDictEqual(kwargs_1, kwargs_3)
def test_non_default_mask_rcnn_box_predictor(self): fc_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } activation: RELU_6 op: FC """ box_predictor_text_proto = """ mask_rcnn_box_predictor { use_dropout: true dropout_keep_probability: 0.8 box_code_size: 3 } """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(fc_hyperparams_text_proto, hyperparams_proto) def mock_fc_argscope_builder(fc_hyperparams_arg, is_training): return (fc_hyperparams_arg, is_training) box_predictor_proto = box_predictor_pb2.BoxPredictor() text_format.Merge(box_predictor_text_proto, box_predictor_proto) box_predictor_proto.mask_rcnn_box_predictor.fc_hyperparams.CopyFrom( hyperparams_proto) box_predictor = box_predictor_builder.build( argscope_fn=mock_fc_argscope_builder, box_predictor_config=box_predictor_proto, is_training=True, num_classes=90) self.assertTrue(box_predictor._use_dropout) self.assertAlmostEqual(box_predictor._dropout_keep_prob, 0.8) self.assertEqual(box_predictor.num_classes, 90) self.assertTrue(box_predictor._is_training) self.assertEqual(box_predictor._box_code_size, 3)
def test_construct_non_default_conv_box_predictor(self): box_predictor_text_proto = """ weight_shared_convolutional_box_predictor { depth: 2 num_layers_before_predictor: 2 kernel_size: 7 box_code_size: 3 class_prediction_bias_init: 4.0 } """ conv_hyperparams_text_proto = """ regularizer { l1_regularizer { } } initializer { truncated_normal_initializer { } } """ hyperparams_proto = hyperparams_pb2.Hyperparams() text_format.Merge(conv_hyperparams_text_proto, hyperparams_proto) def mock_conv_argscope_builder(conv_hyperparams_arg, is_training): return (conv_hyperparams_arg, is_training) box_predictor_proto = box_predictor_pb2.BoxPredictor() text_format.Merge(box_predictor_text_proto, box_predictor_proto) (box_predictor_proto.weight_shared_convolutional_box_predictor. conv_hyperparams.CopyFrom(hyperparams_proto)) box_predictor = box_predictor_builder.build( argscope_fn=mock_conv_argscope_builder, box_predictor_config=box_predictor_proto, is_training=False, num_classes=10) self.assertEqual(box_predictor._depth, 2) self.assertEqual(box_predictor._num_layers_before_predictor, 2) self.assertAlmostEqual(box_predictor._class_prediction_bias_init, 4.0) self.assertEqual(box_predictor.num_classes, 10) self.assertFalse(box_predictor._is_training)
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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = 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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = scope.values()[0] initializer = conv_scope_arguments['weights_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=2. / 100.)
def test_variance_in_range_with_truncated_normal_initializer(self): conv_hyperparams_text_proto = """ regularizer { l2_regularizer { } } initializer { truncated_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 = hyperparams_builder.build(conv_hyperparams_proto, is_training=True) conv_scope_arguments = scope.values()[0] initializer = conv_scope_arguments['weights_initializer'] self._assert_variance_in_range(initializer, shape=[100, 40], variance=0.49, tol=1e-1)
def _build_arg_scope_with_hyperparams(self, hyperparams_text_proto, is_training): hyperparams = hyperparams_pb2.Hyperparams() text_format.Merge(hyperparams_text_proto, hyperparams) return hyperparams_builder.build(hyperparams, is_training=is_training)