Python graph_rewriter_builder.build方法代码示例

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def _save_checkpoint_from_mock_model(self,
                                       checkpoint_path,
                                       use_moving_averages,
                                       enable_quantization=False):
    g = tf.Graph()
    with g.as_default():
      mock_model = FakeModel()
      preprocessed_inputs, true_image_shapes = mock_model.preprocess(
          tf.placeholder(tf.float32, shape=[None, None, None, 3]))
      predictions = mock_model.predict(preprocessed_inputs, true_image_shapes)
      mock_model.postprocess(predictions, true_image_shapes)
      if use_moving_averages:
        tf.train.ExponentialMovingAverage(0.0).apply()
      tf.train.get_or_create_global_step()
      if enable_quantization:
        graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
        graph_rewriter_config.quantization.delay = 500000
        graph_rewriter_fn = graph_rewriter_builder.build(
            graph_rewriter_config, is_training=False)
        graph_rewriter_fn()
      saver = tf.train.Saver()
      init = tf.global_variables_initializer()
      with self.test_session() as sess:
        sess.run(init)
        saver.save(sess, checkpoint_path) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_export_graph_with_image_tensor_input(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=False)
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      output_directory = os.path.join(tmp_dir, 'output')
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      pipeline_config.eval_config.use_moving_averages = False
      exporter.export_inference_graph(
          input_type='image_tensor',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory)
      self.assertTrue(os.path.exists(os.path.join(
          output_directory, 'saved_model', 'saved_model.pb'))) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_write_inference_graph(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=False)
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      output_directory = os.path.join(tmp_dir, 'output')
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      pipeline_config.eval_config.use_moving_averages = False
      exporter.export_inference_graph(
          input_type='image_tensor',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory,
          write_inference_graph=True)
      self.assertTrue(os.path.exists(os.path.join(
          output_directory, 'inference_graph.pbtxt'))) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_export_graph_with_tf_example_input(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=False)
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      output_directory = os.path.join(tmp_dir, 'output')
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      pipeline_config.eval_config.use_moving_averages = False
      exporter.export_inference_graph(
          input_type='tf_example',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory)
      self.assertTrue(os.path.exists(os.path.join(
          output_directory, 'saved_model', 'saved_model.pb'))) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_export_graph_with_encoded_image_string_input(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=False)
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      output_directory = os.path.join(tmp_dir, 'output')
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      pipeline_config.eval_config.use_moving_averages = False
      exporter.export_inference_graph(
          input_type='encoded_image_string_tensor',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory)
      self.assertTrue(os.path.exists(os.path.join(
          output_directory, 'saved_model', 'saved_model.pb'))) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_export_graph_with_moving_averages(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=True)
    output_directory = os.path.join(tmp_dir, 'output')
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      pipeline_config.eval_config.use_moving_averages = True
      exporter.export_inference_graph(
          input_type='image_tensor',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory)
      self.assertTrue(os.path.exists(os.path.join(
          output_directory, 'saved_model', 'saved_model.pb')))
    expected_variables = set(['conv2d/bias', 'conv2d/kernel', 'global_step'])
    actual_variables = set(
        [var_name for var_name, _ in tf.train.list_variables(output_directory)])
    self.assertTrue(expected_variables.issubset(actual_variables)) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def test_export_graph_saves_pipeline_file(self):
    tmp_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
    self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
                                          use_moving_averages=True)
    output_directory = os.path.join(tmp_dir, 'output')
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()
      pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      exporter.export_inference_graph(
          input_type='image_tensor',
          pipeline_config=pipeline_config,
          trained_checkpoint_prefix=trained_checkpoint_prefix,
          output_directory=output_directory)
      expected_pipeline_path = os.path.join(
          output_directory, 'pipeline.config')
      self.assertTrue(os.path.exists(expected_pipeline_path))

      written_pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
      with tf.gfile.GFile(expected_pipeline_path, 'r') as f:
        proto_str = f.read()
        text_format.Merge(proto_str, written_pipeline_config)
        self.assertProtoEquals(pipeline_config, written_pipeline_config) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def testQuantizationBuilderSetsUpCorrectTrainArguments(self):
    with mock.patch.object(
        tf.contrib.quantize, 'create_training_graph') as mock_quant_fn:
      with mock.patch.object(tf.contrib.layers,
                             'summarize_collection') as mock_summarize_col:
        graph_rewriter_proto = graph_rewriter_pb2.GraphRewriter()
        graph_rewriter_proto.quantization.delay = 10
        graph_rewriter_proto.quantization.weight_bits = 8
        graph_rewriter_proto.quantization.activation_bits = 8
        graph_rewrite_fn = graph_rewriter_builder.build(
            graph_rewriter_proto, is_training=True)
        graph_rewrite_fn()
        _, kwargs = mock_quant_fn.call_args
        self.assertEqual(kwargs['input_graph'], tf.get_default_graph())
        self.assertEqual(kwargs['quant_delay'], 10)
        mock_summarize_col.assert_called_with('quant_vars') 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def _export_graph(self, pipeline_config, num_channels=3):
    """Exports a tflite graph."""
    output_dir = self.get_temp_dir()
    trained_checkpoint_prefix = os.path.join(output_dir, 'model.ckpt')
    tflite_graph_file = os.path.join(output_dir, 'tflite_graph.pb')

    quantize = pipeline_config.HasField('graph_rewriter')
    self._save_checkpoint_from_mock_model(
        trained_checkpoint_prefix,
        use_moving_averages=pipeline_config.eval_config.use_moving_averages,
        quantize=quantize,
        num_channels=num_channels)
    with mock.patch.object(
        model_builder, 'build', autospec=True) as mock_builder:
      mock_builder.return_value = FakeModel()

      with tf.Graph().as_default():
        export_tflite_ssd_graph_lib.export_tflite_graph(
            pipeline_config=pipeline_config,
            trained_checkpoint_prefix=trained_checkpoint_prefix,
            output_dir=output_dir,
            add_postprocessing_op=False,
            max_detections=10,
            max_classes_per_detection=1)
    return tflite_graph_file 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def _save_checkpoint_from_mock_model(self,
                                       checkpoint_path,
                                       use_moving_averages,
                                       quantize=False,
                                       num_channels=3):
    g = tf.Graph()
    with g.as_default():
      mock_model = FakeModel()
      inputs = tf.placeholder(tf.float32, shape=[1, 10, 10, num_channels])
      mock_model.predict(inputs, true_image_shapes=None)
      if use_moving_averages:
        tf.train.ExponentialMovingAverage(0.0).apply()
      tf.train.get_or_create_global_step()
      if quantize:
        graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
        graph_rewriter_config.quantization.delay = 500000
        graph_rewriter_fn = graph_rewriter_builder.build(
            graph_rewriter_config, is_training=False)
        graph_rewriter_fn()

      saver = tf.train.Saver()
      init = tf.global_variables_initializer()
      with self.test_session() as sess:
        sess.run(init)
        saver.save(sess, checkpoint_path) 

# 需要导入模块: from object_detection.builders import graph_rewriter_builder [as 别名]
# 或者: from object_detection.builders.graph_rewriter_builder import build [as 别名]
def testQuantizationBuilderSetsUpCorrectTrainArguments(self):
    with mock.patch.object(
        tf.contrib.quantize,
        'experimental_create_training_graph') as mock_quant_fn:
      with mock.patch.object(tf.contrib.layers,
                             'summarize_collection') as mock_summarize_col:
        graph_rewriter_proto = graph_rewriter_pb2.GraphRewriter()
        graph_rewriter_proto.quantization.delay = 10
        graph_rewriter_proto.quantization.weight_bits = 8
        graph_rewriter_proto.quantization.activation_bits = 8
        graph_rewrite_fn = graph_rewriter_builder.build(
            graph_rewriter_proto, is_training=True)
        graph_rewrite_fn()
        _, kwargs = mock_quant_fn.call_args
        self.assertEqual(kwargs['input_graph'], tf.get_default_graph())
        self.assertEqual(kwargs['quant_delay'], 10)
        mock_summarize_col.assert_called_with('quant_vars')