def testNewFocalLossParameters(self): """Tests that the loss weight ratio is updated appropriately.""" original_alpha = 1.0 original_gamma = 1.0 new_alpha = 0.3 new_gamma = 2.0 hparams = tf.contrib.training.HParams(focal_loss_alpha=new_alpha, focal_loss_gamma=new_gamma) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() classification_loss = pipeline_config.model.ssd.loss.classification_loss classification_loss.weighted_sigmoid_focal.alpha = original_alpha classification_loss.weighted_sigmoid_focal.gamma = original_gamma _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) classification_loss = configs["model"].ssd.loss.classification_loss self.assertAlmostEqual( new_alpha, classification_loss.weighted_sigmoid_focal.alpha) self.assertAlmostEqual( new_gamma, classification_loss.weighted_sigmoid_focal.gamma)
def test_get_configs_from_pipeline_file(self): """Test that proto configs can be read from pipeline config file.""" pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.faster_rcnn.num_classes = 10 pipeline_config.train_config.batch_size = 32 pipeline_config.train_input_reader.label_map_path = "path/to/label_map" pipeline_config.eval_config.num_examples = 20 pipeline_config.eval_input_reader.queue_capacity = 100 _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) self.assertProtoEquals(pipeline_config.model, configs["model"]) self.assertProtoEquals(pipeline_config.train_config, configs["train_config"]) self.assertProtoEquals(pipeline_config.train_input_reader, configs["train_input_config"]) self.assertProtoEquals(pipeline_config.eval_config, configs["eval_config"]) self.assertProtoEquals(pipeline_config.eval_input_reader, configs["eval_input_config"])
def testKeyValueOverrideBadKey(self): """Tests that overwriting with a bad key causes an exception.""" pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() configs = self._create_and_load_test_configs(pipeline_config) hparams = tf.contrib.training.HParams( **{"train_config.no_such_field": 10}) with self.assertRaises(ValueError): config_util.merge_external_params_with_configs(configs, hparams)
def testOverwriteBatchSizeWithBadValueType(self): """Tests that overwriting with a bad valuye type causes an exception.""" pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_config.batch_size = 2 configs = self._create_and_load_test_configs(pipeline_config) # Type should be an integer, but we're passing a string "10". hparams = tf.contrib.training.HParams( **{"train_config.batch_size": "10"}) with self.assertRaises(TypeError): config_util.merge_external_params_with_configs(configs, hparams)
def testOverwriteBatchSizeWithKeyValue(self): """Tests that batch size is overwritten based on key/value.""" pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_config.batch_size = 2 configs = self._create_and_load_test_configs(pipeline_config) hparams = tf.contrib.training.HParams( **{"train_config.batch_size": 10}) configs = config_util.merge_external_params_with_configs( configs, hparams) new_batch_size = configs["train_config"].batch_size self.assertEqual(10, new_batch_size)
def testGetNumberOfClasses(self): """Tests that number of classes can be retrieved.""" pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.faster_rcnn.num_classes = 20 _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) number_of_classes = config_util.get_number_of_classes(configs["model"]) self.assertEqual(20, number_of_classes)
def testUseMovingAverageForEval(self): use_moving_averages_orig = False pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.eval_config.use_moving_averages = use_moving_averages_orig _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, eval_with_moving_averages=True) self.assertEqual(True, configs["eval_config"].use_moving_averages)
def main(argv): del argv # Unused. flags.mark_flag_as_required('output_directory') flags.mark_flag_as_required('pipeline_config_path') flags.mark_flag_as_required('trained_checkpoint_prefix') pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f: text_format.Merge(f.read(), pipeline_config) text_format.Merge(FLAGS.config_override, pipeline_config) export_tflite_ssd_graph_lib.export_tflite_graph( pipeline_config, FLAGS.trained_checkpoint_prefix, FLAGS.output_directory, FLAGS.add_postprocessing_op, FLAGS.max_detections, FLAGS.max_classes_per_detection)
def test_save_pipeline_config(self): """Tests that the pipeline config is properly saved to disk.""" pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.faster_rcnn.num_classes = 10 pipeline_config.train_config.batch_size = 32 pipeline_config.train_input_reader.label_map_path = "path/to/label_map" pipeline_config.eval_config.num_examples = 20 pipeline_config.eval_input_reader.queue_capacity = 100 config_util.save_pipeline_config(pipeline_config, self.get_temp_dir()) configs = config_util.get_configs_from_pipeline_file( os.path.join(self.get_temp_dir(), "pipeline.config")) pipeline_config_reconstructed = ( config_util.create_pipeline_proto_from_configs(configs)) self.assertEqual(pipeline_config, pipeline_config_reconstructed)
def testNewBatchSizeWithClipping(self): """Tests that batch size is clipped to 1 from below.""" original_batch_size = 2 hparams = tf.contrib.training.HParams(batch_size=0.5) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_config.batch_size = original_batch_size _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) new_batch_size = configs["train_config"].batch_size self.assertEqual(1, new_batch_size) # Clipped to 1.0.
def testNewBatchSize(self): """Tests that batch size is updated appropriately.""" original_batch_size = 2 hparams = tf.contrib.training.HParams(batch_size=16) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_config.batch_size = original_batch_size _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) new_batch_size = configs["train_config"].batch_size self.assertEqual(16, new_batch_size)
def get_configs_from_pipeline_file(pipeline_config_path): """Reads config from a file containing pipeline_pb2.TrainEvalPipelineConfig. Args: pipeline_config_path: Path to pipeline_pb2.TrainEvalPipelineConfig text proto. Returns: Dictionary of configuration objects. Keys are `model`, `train_config`, `train_input_config`, `eval_config`, `eval_input_config`. Value are the corresponding config objects. """ pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() with tf.gfile.GFile(pipeline_config_path, "r") as f: proto_str = f.read() text_format.Merge(proto_str, pipeline_config) return create_configs_from_pipeline_proto(pipeline_config)
def test_export_tflite_graph_without_moving_averages(self): pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.eval_config.use_moving_averages = False pipeline_config.model.ssd.image_resizer.fixed_shape_resizer.height = 10 pipeline_config.model.ssd.image_resizer.fixed_shape_resizer.width = 10 pipeline_config.model.ssd.num_classes = 2 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.y_scale = 10.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.x_scale = 10.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.height_scale = 5.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.width_scale = 5.0 tflite_graph_file = self._export_graph(pipeline_config) self.assertTrue(os.path.exists(tflite_graph_file)) (box_encodings_np, class_predictions_np ) = self._import_graph_and_run_inference(tflite_graph_file) self.assertAllClose(box_encodings_np, [[[0.0, 0.0, 0.5, 0.5], [0.5, 0.5, 0.8, 0.8]]]) self.assertAllClose(class_predictions_np, [[[0.7, 0.6], [0.9, 0.0]]])
def testTrainShuffle(self): """Tests that `train_shuffle` keyword arguments are applied correctly.""" original_shuffle = True desired_shuffle = False pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_input_reader.shuffle = original_shuffle _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, train_shuffle=desired_shuffle) train_shuffle = configs["train_input_config"].shuffle self.assertEqual(desired_shuffle, train_shuffle)
def test_create_pipeline_proto_from_configs(self): """Tests that proto can be reconstructed from configs dictionary.""" pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.faster_rcnn.num_classes = 10 pipeline_config.train_config.batch_size = 32 pipeline_config.train_input_reader.label_map_path = "path/to/label_map" pipeline_config.eval_config.num_examples = 20 pipeline_config.eval_input_reader.queue_capacity = 100 _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) pipeline_config_reconstructed = ( config_util.create_pipeline_proto_from_configs(configs)) self.assertEqual(pipeline_config, pipeline_config_reconstructed)
def testNewMomentumOptimizerValue(self): """Tests that new momentum value is updated appropriately.""" original_momentum_value = 0.4 hparams = tf.contrib.training.HParams(momentum_optimizer_value=1.1) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() optimizer_config = pipeline_config.train_config.optimizer.rms_prop_optimizer optimizer_config.momentum_optimizer_value = original_momentum_value _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) optimizer_config = configs["train_config"].optimizer.rms_prop_optimizer new_momentum_value = optimizer_config.momentum_optimizer_value self.assertAlmostEqual(1.0, new_momentum_value) # Clipped to 1.0.
def main(_): pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f: text_format.Merge(f.read(), pipeline_config) text_format.Merge(FLAGS.config_override, pipeline_config) if FLAGS.input_shape: input_shape = [ int(dim) if dim != '-1' else None for dim in FLAGS.input_shape.split(',') ] else: input_shape = None exporter.export_inference_graph( FLAGS.input_type, pipeline_config, FLAGS.trained_checkpoint_prefix, FLAGS.output_directory, input_shape=input_shape, write_inference_graph=FLAGS.write_inference_graph)
def testNewTrainInputPathList(self): """Tests that train input path can be overwritten with multiple files.""" original_train_path = ["path/to/data"] new_train_path = ["another/path/to/data", "yet/another/path/to/data"] pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() reader_config = pipeline_config.train_input_reader.tf_record_input_reader reader_config.input_path.extend(original_train_path) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, train_input_path=new_train_path) reader_config = configs["train_input_config"].tf_record_input_reader final_path = reader_config.input_path self.assertEqual(new_train_path, final_path)
def testOverWriteRetainOriginalImages(self): """Tests that `train_shuffle` keyword arguments are applied correctly.""" original_retain_original_images = True desired_retain_original_images = False pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.eval_config.retain_original_images = ( original_retain_original_images) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, retain_original_images_in_eval=desired_retain_original_images) retain_original_images = configs["eval_config"].retain_original_images self.assertEqual(desired_retain_original_images, retain_original_images)
def test_export_tflite_graph_with_softmax_score_conversion(self): pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.eval_config.use_moving_averages = False pipeline_config.model.ssd.post_processing.score_converter = ( post_processing_pb2.PostProcessing.SOFTMAX) pipeline_config.model.ssd.image_resizer.fixed_shape_resizer.height = 10 pipeline_config.model.ssd.image_resizer.fixed_shape_resizer.width = 10 pipeline_config.model.ssd.num_classes = 2 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.y_scale = 10.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.x_scale = 10.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.height_scale = 5.0 pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.width_scale = 5.0 tflite_graph_file = self._export_graph(pipeline_config) self.assertTrue(os.path.exists(tflite_graph_file)) (box_encodings_np, class_predictions_np ) = self._import_graph_and_run_inference(tflite_graph_file) self.assertAllClose(box_encodings_np, [[[0.0, 0.0, 0.5, 0.5], [0.5, 0.5, 0.8, 0.8]]]) self.assertAllClose(class_predictions_np, [[[0.524979, 0.475021], [0.710949, 0.28905]]])
def test_create_configs_from_pipeline_proto(self): """Tests creating configs dictionary from pipeline proto.""" pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.faster_rcnn.num_classes = 10 pipeline_config.train_config.batch_size = 32 pipeline_config.train_input_reader.label_map_path = "path/to/label_map" pipeline_config.eval_config.num_examples = 20 pipeline_config.eval_input_reader.queue_capacity = 100 configs = config_util.create_configs_from_pipeline_proto( pipeline_config) self.assertProtoEquals(pipeline_config.model, configs["model"]) self.assertProtoEquals(pipeline_config.train_config, configs["train_config"]) self.assertProtoEquals(pipeline_config.train_input_reader, configs["train_input_config"]) self.assertProtoEquals(pipeline_config.eval_config, configs["eval_config"]) self.assertProtoEquals(pipeline_config.eval_input_reader, configs["eval_input_config"])
def testNewMaskType(self): """Tests that mask type can be overwritten in input readers.""" original_mask_type = input_reader_pb2.NUMERICAL_MASKS new_mask_type = input_reader_pb2.PNG_MASKS pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() train_input_reader = pipeline_config.train_input_reader train_input_reader.mask_type = original_mask_type eval_input_reader = pipeline_config.eval_input_reader eval_input_reader.mask_type = original_mask_type _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, mask_type=new_mask_type) self.assertEqual(new_mask_type, configs["train_input_config"].mask_type) self.assertEqual(new_mask_type, configs["eval_input_config"].mask_type)
def create_pipeline_proto_from_configs(configs): """Creates a pipeline_pb2.TrainEvalPipelineConfig from configs dictionary. This function performs the inverse operation of create_configs_from_pipeline_proto(). Args: configs: Dictionary of configs. See get_configs_from_pipeline_file(). Returns: A fully populated pipeline_pb2.TrainEvalPipelineConfig. """ pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.CopyFrom(configs["model"]) pipeline_config.train_config.CopyFrom(configs["train_config"]) pipeline_config.train_input_reader.CopyFrom(configs["train_input_config"]) pipeline_config.eval_config.CopyFrom(configs["eval_config"]) pipeline_config.eval_input_reader.CopyFrom(configs["eval_input_config"]) if "graph_rewriter_config" in configs: pipeline_config.graph_rewriter.CopyFrom( configs["graph_rewriter_config"]) return pipeline_config
def testDontOverwriteEmptyLabelMapPath(self): """Tests that label map path will not by overwritten with empty string.""" original_label_map_path = "path/to/original/label_map" new_label_map_path = "" pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() train_input_reader = pipeline_config.train_input_reader train_input_reader.label_map_path = original_label_map_path eval_input_reader = pipeline_config.eval_input_reader eval_input_reader.label_map_path = original_label_map_path _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, label_map_path=new_label_map_path) self.assertEqual(original_label_map_path, configs["train_input_config"].label_map_path) self.assertEqual(original_label_map_path, configs["eval_input_config"].label_map_path)
def testMergingKeywordArguments(self): """Tests that keyword arguments get merged as do hyperparameters.""" original_num_train_steps = 100 original_num_eval_steps = 5 desired_num_train_steps = 10 desired_num_eval_steps = 1 pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.train_config.num_steps = original_num_train_steps pipeline_config.eval_config.num_examples = original_num_eval_steps _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, train_steps=desired_num_train_steps, eval_steps=desired_num_eval_steps) train_steps = configs["train_config"].num_steps eval_steps = configs["eval_config"].num_examples self.assertEqual(desired_num_train_steps, train_steps) self.assertEqual(desired_num_eval_steps, eval_steps)
def testNewClassificationLocalizationWeightRatio(self): """Tests that the loss weight ratio is updated appropriately.""" original_localization_weight = 0.1 original_classification_weight = 0.2 new_weight_ratio = 5.0 hparams = tf.contrib.training.HParams( classification_localization_weight_ratio=new_weight_ratio) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() pipeline_config.model.ssd.loss.localization_weight = ( original_localization_weight) pipeline_config.model.ssd.loss.classification_weight = ( original_classification_weight) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) loss = configs["model"].ssd.loss self.assertAlmostEqual(1.0, loss.localization_weight) self.assertAlmostEqual(new_weight_ratio, loss.classification_weight)
def _assertOptimizerWithNewLearningRate(self, optimizer_name): """Asserts successful updating of all learning rate schemes.""" original_learning_rate = 0.7 learning_rate_scaling = 0.1 warmup_learning_rate = 0.07 hparams = tf.contrib.training.HParams(learning_rate=0.15) pipeline_config_path = os.path.join(self.get_temp_dir(), "pipeline.config") # Constant learning rate. pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() optimizer = getattr(pipeline_config.train_config.optimizer, optimizer_name) _update_optimizer_with_constant_learning_rate(optimizer, original_learning_rate) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) optimizer = getattr(configs["train_config"].optimizer, optimizer_name) constant_lr = optimizer.learning_rate.constant_learning_rate self.assertAlmostEqual(hparams.learning_rate, constant_lr.learning_rate) # Exponential decay learning rate. pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() optimizer = getattr(pipeline_config.train_config.optimizer, optimizer_name) _update_optimizer_with_exponential_decay_learning_rate( optimizer, original_learning_rate) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) optimizer = getattr(configs["train_config"].optimizer, optimizer_name) exponential_lr = optimizer.learning_rate.exponential_decay_learning_rate self.assertAlmostEqual(hparams.learning_rate, exponential_lr.initial_learning_rate) # Manual step learning rate. pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() optimizer = getattr(pipeline_config.train_config.optimizer, optimizer_name) _update_optimizer_with_manual_step_learning_rate( optimizer, original_learning_rate, learning_rate_scaling) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) optimizer = getattr(configs["train_config"].optimizer, optimizer_name) manual_lr = optimizer.learning_rate.manual_step_learning_rate self.assertAlmostEqual(hparams.learning_rate, manual_lr.initial_learning_rate) for i, schedule in enumerate(manual_lr.schedule): self.assertAlmostEqual( hparams.learning_rate * learning_rate_scaling**i, schedule.learning_rate) # Cosine decay learning rate. pipeline_config = pipeline_pb2.TrainEvalPipelineConfig() optimizer = getattr(pipeline_config.train_config.optimizer, optimizer_name) _update_optimizer_with_cosine_decay_learning_rate( optimizer, original_learning_rate, warmup_learning_rate) _write_config(pipeline_config, pipeline_config_path) configs = config_util.get_configs_from_pipeline_file( pipeline_config_path) configs = config_util.merge_external_params_with_configs( configs, hparams) optimizer = getattr(configs["train_config"].optimizer, optimizer_name) cosine_lr = optimizer.learning_rate.cosine_decay_learning_rate self.assertAlmostEqual(hparams.learning_rate, cosine_lr.learning_rate_base) warmup_scale_factor = warmup_learning_rate / original_learning_rate self.assertAlmostEqual(hparams.learning_rate * warmup_scale_factor, cosine_lr.warmup_learning_rate)