Python signature_def_utils_impl.predict_signature_def方法代碼示例

# 需要導入模塊: from tensorflow.python.saved_model import signature_def_utils_impl [as 別名]
# 或者: from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def [as 別名]
def _store_tf(self, name, session):

        json_model_file = open(os.path.join(self.model_path, name + '.json'), "r").read()
        loaded_model = model_from_json(json_model_file)
        loaded_model.load_weights(os.path.join(self.model_path, name + '.h5'))

        builder = saved_model_builder.SavedModelBuilder(os.path.join(self.model_path, 'tf.txt'))
        signature = predict_signature_def(inputs={'states': loaded_model.input},
                                          outputs={'price': loaded_model.output})

        builder.add_meta_graph_and_variables(sess=session,
                                             tags=[tag_constants.SERVING],
                                             signature_def_map={'helpers': signature})
        builder.save()

        _logger.info("Saved tf.txt model to disk") 

# 需要導入模塊: from tensorflow.python.saved_model import signature_def_utils_impl [as 別名]
# 或者: from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def [as 別名]
def saveWithSavedModel():
    # K.set_learning_phase(0)  # all new operations will be in test mode from now on

    # wordIndex = loadWordIndex()
    model = createModel()
    model.load_weights(KERAS_WEIGHTS_FILE)


    export_path = os.path.join(PUNCTUATOR_DIR, 'graph') # where to save the exported graph

    shutil.rmtree(export_path, True)
    export_version = 1 # version number (integer)

    import tensorflow as tf
    sess = tf.Session()

    saver = tf.train.Saver(sharded=True)
    from tensorflow.contrib.session_bundle import exporter
    model_exporter = exporter.Exporter(saver)
    signature = exporter.classification_signature(input_tensor=model.input,scores_tensor=model.output)
    # model_exporter.init(sess.graph.as_graph_def(),default_graph_signature=signature)
    tf.initialize_all_variables().run(session=sess)
    # model_exporter.export(export_path, tf.constant(export_version), sess)
    from tensorflow.python.saved_model import builder as saved_model_builder
    builder = saved_model_builder.SavedModelBuilder(export_path)
    from tensorflow.python.saved_model import signature_constants
    from tensorflow.python.saved_model import tag_constants
    legacy_init_op = tf.group(tf.tables_initializer(), name='legacy_init_op')
    from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def
    signature_def = predict_signature_def(
        {signature_constants.PREDICT_INPUTS: model.input},
        {signature_constants.PREDICT_OUTPUTS: model.output})
    builder.add_meta_graph_and_variables(
        sess, [tag_constants.SERVING],
        signature_def_map={
            signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
                signature_def
        },
        legacy_init_op=legacy_init_op)
    builder.save() 

# 需要導入模塊: from tensorflow.python.saved_model import signature_def_utils_impl [as 別名]
# 或者: from tensorflow.python.saved_model.signature_def_utils_impl import predict_signature_def [as 別名]
def main():
    args = _parse_args()

    trained_checkpoint_prefix = tf.train.latest_checkpoint(args.model_dir)

    # Each model folder must be named '0', '1', ...
    export_dir = os.path.join(args.model_dir, 'models', '0')
    shutil.rmtree(export_dir, ignore_errors=True)

    with tf.compat.v1.Session(
            graph=tf.Graph(),
            config=tf.compat.v1.ConfigProto(allow_soft_placement=True)) as sess:
        # Restore from checkpoint
        loader = tf.compat.v1.train.import_meta_graph(
                trained_checkpoint_prefix + '.meta')

        loader.restore(sess, trained_checkpoint_prefix)
        
        # Export checkpoint to SavedModel
        builder = tf.compat.v1.saved_model.builder.SavedModelBuilder(export_dir)

        images = sess.graph.get_tensor_by_name('inputs/split_images:0')
        is_training = sess.graph.get_tensor_by_name('inputs/is_training:0')
        predictions = sess.graph.get_tensor_by_name('predictions:0')

        signature = predict_signature_def(
                inputs={'images': images, 'is_training': is_training},
                outputs={'predictions': predictions})

        builder.add_meta_graph_and_variables(
                sess,
                [tf.saved_model.SERVING],
                strip_default_attrs=True,
                signature_def_map={'predict': signature})

        builder.save()