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_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 _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 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 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_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(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_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 _build_ssd_feature_extractor(feature_extractor_config, is_training, reuse_weights=None): """Builds a ssd_meta_arch.SSDFeatureExtractor based on config. Args: feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto. is_training: True if this feature extractor is being built for training. reuse_weights: if the feature extractor should reuse weights. Returns: ssd_meta_arch.SSDFeatureExtractor based on config. Raises: ValueError: On invalid feature extractor type. """ feature_type = feature_extractor_config.type depth_multiplier = feature_extractor_config.depth_multiplier min_depth = feature_extractor_config.min_depth pad_to_multiple = feature_extractor_config.pad_to_multiple use_explicit_padding = feature_extractor_config.use_explicit_padding use_depthwise = feature_extractor_config.use_depthwise conv_hyperparams = hyperparams_builder.build( feature_extractor_config.conv_hyperparams, is_training) override_base_feature_extractor_hyperparams = ( feature_extractor_config.override_base_feature_extractor_hyperparams) if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP: raise ValueError( 'Unknown ssd feature_extractor: {}'.format(feature_type)) feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type] return feature_extractor_class( is_training, depth_multiplier, min_depth, pad_to_multiple, conv_hyperparams, reuse_weights, use_explicit_padding, use_depthwise, override_base_feature_extractor_hyperparams)
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)
def _build_ssd_feature_extractor(feature_extractor_config, is_training, reuse_weights=None): """Builds a ssd_meta_arch.SSDFeatureExtractor based on config. Args: feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto. is_training: True if this feature extractor is being built for training. reuse_weights: if the feature extractor should reuse weights. Returns: ssd_meta_arch.SSDFeatureExtractor based on config. Raises: ValueError: On invalid feature extractor type. """ feature_type = feature_extractor_config.type depth_multiplier = feature_extractor_config.depth_multiplier min_depth = feature_extractor_config.min_depth pad_to_multiple = feature_extractor_config.pad_to_multiple use_explicit_padding = feature_extractor_config.use_explicit_padding use_depthwise = feature_extractor_config.use_depthwise conv_hyperparams = hyperparams_builder.build( feature_extractor_config.conv_hyperparams, is_training) override_base_feature_extractor_hyperparams = ( feature_extractor_config.override_base_feature_extractor_hyperparams) if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP: raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type)) feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type] kwargs = { 'is_training': is_training, 'depth_multiplier': depth_multiplier, 'min_depth': min_depth, 'pad_to_multiple': pad_to_multiple, 'conv_hyperparams_fn': conv_hyperparams, 'reuse_weights': reuse_weights, 'use_explicit_padding': use_explicit_padding, 'use_depthwise': use_depthwise, 'override_base_feature_extractor_hyperparams': override_base_feature_extractor_hyperparams } if feature_extractor_config.HasField('fpn'): kwargs.update({ 'fpn_min_level': feature_extractor_config.fpn.min_level, 'fpn_max_level': feature_extractor_config.fpn.max_level, 'additional_layer_depth': feature_extractor_config.fpn.additional_layer_depth, }) return feature_extractor_class(**kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries): """Builds a Faster R-CNN or R-FCN detection model based on the model config. Builds R-FCN model if the second_stage_box_predictor in the config is of type `rfcn_box_predictor` else builds a Faster R-CNN model. Args: frcnn_config: A faster_rcnn.proto object containing the config for the desired FasterRCNNMetaArch or RFCNMetaArch. is_training: True if this model is being built for training purposes. add_summaries: Whether to add tf summaries in the model. Returns: FasterRCNNMetaArch based on the config. Raises: ValueError: If frcnn_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = frcnn_config.num_classes image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer) feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training, frcnn_config.inplace_batchnorm_update) number_of_stages = frcnn_config.number_of_stages first_stage_anchor_generator = anchor_generator_builder.build( frcnn_config.first_stage_anchor_generator) first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build( frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training) first_stage_box_predictor_kernel_size = ( frcnn_config.first_stage_box_predictor_kernel_size) first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size first_stage_positive_balance_fraction = ( frcnn_config.first_stage_positive_balance_fraction) first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold first_stage_max_proposals = frcnn_config.first_stage_max_proposals first_stage_loc_loss_weight = ( frcnn_config.first_stage_localization_loss_weight) first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight initial_crop_size = frcnn_config.initial_crop_size maxpool_kernel_size = frcnn_config.maxpool_kernel_size maxpool_stride = frcnn_config.maxpool_stride second_stage_box_predictor = box_predictor_builder.build( hyperparams_builder.build, frcnn_config.second_stage_box_predictor, is_training=is_training, num_classes=num_classes) second_stage_batch_size = frcnn_config.second_stage_batch_size second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction (second_stage_non_max_suppression_fn, second_stage_score_conversion_fn) = post_processing_builder.build( frcnn_config.second_stage_post_processing) second_stage_localization_loss_weight = ( frcnn_config.second_stage_localization_loss_weight) second_stage_classification_loss = ( losses_builder.build_faster_rcnn_classification_loss( frcnn_config.second_stage_classification_loss)) second_stage_classification_loss_weight = ( frcnn_config.second_stage_classification_loss_weight) second_stage_mask_prediction_loss_weight = ( frcnn_config.second_stage_mask_prediction_loss_weight) hard_example_miner = None if frcnn_config.HasField('hard_example_miner'): hard_example_miner = losses_builder.build_hard_example_miner( frcnn_config.hard_example_miner, second_stage_classification_loss_weight, second_stage_localization_loss_weight) common_kwargs = { 'is_training': is_training, 'num_classes': num_classes, 'image_resizer_fn': image_resizer_fn, 'feature_extractor': feature_extractor, 'number_of_stages': number_of_stages, 'first_stage_anchor_generator': first_stage_anchor_generator, 'first_stage_atrous_rate': first_stage_atrous_rate, 'first_stage_box_predictor_arg_scope_fn': first_stage_box_predictor_arg_scope_fn, 'first_stage_box_predictor_kernel_size': first_stage_box_predictor_kernel_size, 'first_stage_box_predictor_depth': first_stage_box_predictor_depth, 'first_stage_minibatch_size': first_stage_minibatch_size, 'first_stage_positive_balance_fraction': first_stage_positive_balance_fraction, 'first_stage_nms_score_threshold': first_stage_nms_score_threshold, 'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold, 'first_stage_max_proposals': first_stage_max_proposals, 'first_stage_localization_loss_weight': first_stage_loc_loss_weight, 'first_stage_objectness_loss_weight': first_stage_obj_loss_weight, 'second_stage_batch_size': second_stage_batch_size, 'second_stage_balance_fraction': second_stage_balance_fraction, 'second_stage_non_max_suppression_fn': second_stage_non_max_suppression_fn, 'second_stage_score_conversion_fn': second_stage_score_conversion_fn, 'second_stage_localization_loss_weight': second_stage_localization_loss_weight, 'second_stage_classification_loss': second_stage_classification_loss, 'second_stage_classification_loss_weight': second_stage_classification_loss_weight, 'hard_example_miner': hard_example_miner, 'add_summaries': add_summaries } if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor): return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=second_stage_box_predictor, **common_kwargs) else: return faster_rcnn_meta_arch.FasterRCNNMetaArch( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, second_stage_mask_rcnn_box_predictor=second_stage_box_predictor, second_stage_mask_prediction_loss_weight=( second_stage_mask_prediction_loss_weight), **common_kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries): """Builds a Faster R-CNN or R-FCN detection model based on the model config. Builds R-FCN model if the second_stage_box_predictor in the config is of type `rfcn_box_predictor` else builds a Faster R-CNN model. Args: frcnn_config: A faster_rcnn.proto object containing the config for the desired FasterRCNNMetaArch or RFCNMetaArch. is_training: True if this model is being built for training purposes. add_summaries: Whether to add tf summaries in the model. Returns: FasterRCNNMetaArch based on the config. Raises: ValueError: If frcnn_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = frcnn_config.num_classes image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer) feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training, frcnn_config.inplace_batchnorm_update) number_of_stages = frcnn_config.number_of_stages first_stage_anchor_generator = anchor_generator_builder.build( frcnn_config.first_stage_anchor_generator) first_stage_target_assigner = target_assigner.create_target_assigner( 'FasterRCNN', 'proposal', use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher) first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build( frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training) first_stage_box_predictor_kernel_size = ( frcnn_config.first_stage_box_predictor_kernel_size) first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size # TODO(bhattad): When eval is supported using static shapes, add separate # use_static_shapes_for_trainig and use_static_shapes_for_evaluation. use_static_shapes = frcnn_config.use_static_shapes and is_training first_stage_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=frcnn_config.first_stage_positive_balance_fraction, is_static=frcnn_config.use_static_balanced_label_sampler and is_training) first_stage_max_proposals = frcnn_config.first_stage_max_proposals if (frcnn_config.first_stage_nms_iou_threshold < 0 or frcnn_config.first_stage_nms_iou_threshold > 1.0): raise ValueError('iou_threshold not in [0, 1.0].') if (is_training and frcnn_config.second_stage_batch_size > first_stage_max_proposals): raise ValueError('second_stage_batch_size should be no greater than ' 'first_stage_max_proposals.') first_stage_non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=frcnn_config.first_stage_nms_score_threshold, iou_thresh=frcnn_config.first_stage_nms_iou_threshold, max_size_per_class=frcnn_config.first_stage_max_proposals, max_total_size=frcnn_config.first_stage_max_proposals, use_static_shapes=use_static_shapes and is_training) first_stage_loc_loss_weight = ( frcnn_config.first_stage_localization_loss_weight) first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight initial_crop_size = frcnn_config.initial_crop_size maxpool_kernel_size = frcnn_config.maxpool_kernel_size maxpool_stride = frcnn_config.maxpool_stride second_stage_target_assigner = target_assigner.create_target_assigner( 'FasterRCNN', 'detection', use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher) second_stage_box_predictor = box_predictor_builder.build( hyperparams_builder.build, frcnn_config.second_stage_box_predictor, is_training=is_training, num_classes=num_classes) second_stage_batch_size = frcnn_config.second_stage_batch_size second_stage_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=frcnn_config.second_stage_balance_fraction, is_static=frcnn_config.use_static_balanced_label_sampler and is_training) (second_stage_non_max_suppression_fn, second_stage_score_conversion_fn ) = post_processing_builder.build(frcnn_config.second_stage_post_processing) second_stage_localization_loss_weight = ( frcnn_config.second_stage_localization_loss_weight) second_stage_classification_loss = ( losses_builder.build_faster_rcnn_classification_loss( frcnn_config.second_stage_classification_loss)) second_stage_classification_loss_weight = ( frcnn_config.second_stage_classification_loss_weight) second_stage_mask_prediction_loss_weight = ( frcnn_config.second_stage_mask_prediction_loss_weight) hard_example_miner = None if frcnn_config.HasField('hard_example_miner'): hard_example_miner = losses_builder.build_hard_example_miner( frcnn_config.hard_example_miner, second_stage_classification_loss_weight, second_stage_localization_loss_weight) crop_and_resize_fn = ( ops.matmul_crop_and_resize if frcnn_config.use_matmul_crop_and_resize else ops.native_crop_and_resize) clip_anchors_to_image = ( frcnn_config.clip_anchors_to_image) common_kwargs = { 'is_training': is_training, 'num_classes': num_classes, 'image_resizer_fn': image_resizer_fn, 'feature_extractor': feature_extractor, 'number_of_stages': number_of_stages, 'first_stage_anchor_generator': first_stage_anchor_generator, 'first_stage_target_assigner': first_stage_target_assigner, 'first_stage_atrous_rate': first_stage_atrous_rate, 'first_stage_box_predictor_arg_scope_fn': first_stage_box_predictor_arg_scope_fn, 'first_stage_box_predictor_kernel_size': first_stage_box_predictor_kernel_size, 'first_stage_box_predictor_depth': first_stage_box_predictor_depth, 'first_stage_minibatch_size': first_stage_minibatch_size, 'first_stage_sampler': first_stage_sampler, 'first_stage_non_max_suppression_fn': first_stage_non_max_suppression_fn, 'first_stage_max_proposals': first_stage_max_proposals, 'first_stage_localization_loss_weight': first_stage_loc_loss_weight, 'first_stage_objectness_loss_weight': first_stage_obj_loss_weight, 'second_stage_target_assigner': second_stage_target_assigner, 'second_stage_batch_size': second_stage_batch_size, 'second_stage_sampler': second_stage_sampler, 'second_stage_non_max_suppression_fn': second_stage_non_max_suppression_fn, 'second_stage_score_conversion_fn': second_stage_score_conversion_fn, 'second_stage_localization_loss_weight': second_stage_localization_loss_weight, 'second_stage_classification_loss': second_stage_classification_loss, 'second_stage_classification_loss_weight': second_stage_classification_loss_weight, 'hard_example_miner': hard_example_miner, 'add_summaries': add_summaries, 'crop_and_resize_fn': crop_and_resize_fn, 'clip_anchors_to_image': clip_anchors_to_image, 'use_static_shapes': use_static_shapes, 'resize_masks': frcnn_config.resize_masks } if isinstance(second_stage_box_predictor, rfcn_box_predictor.RfcnBoxPredictor): return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=second_stage_box_predictor, **common_kwargs) else: return faster_rcnn_meta_arch.FasterRCNNMetaArch( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, second_stage_mask_rcnn_box_predictor=second_stage_box_predictor, second_stage_mask_prediction_loss_weight=( second_stage_mask_prediction_loss_weight), **common_kwargs)