Function load_hdf5_graph

tensorlayer/files/utils.py:299–352

Restore TL model archtecture from a a pickle file. Support loading model weights. Parameters ----------- filepath : str The name of model file. load_weights : bool Whether to load model weights. Returns -------- network : TensorLayer Model. Examples

(filepath='model.hdf5', load_weights=False)

def load_hdf5_graph(filepath='model.hdf5', load_weights=False):
    """Restore TL model archtecture from a a pickle file. Support loading model weights.

    Parameters
    -----------
    filepath : str
        The name of model file.
    load_weights : bool
        Whether to load model weights.

    Returns
    --------
    network : TensorLayer Model.

    Examples
    --------
    - see ``tl.files.save_hdf5_graph``
    """
    logging.info("[*] Loading TL model from {}, loading weights={}".format(filepath, load_weights))

    f = h5py.File(filepath, 'r')

    model_config_str = f.attrs["model_config"].decode('utf8')
    model_config = eval(model_config_str)

    # version_info_str = f.attrs["version_info"].decode('utf8')
    # version_info = eval(version_info_str)
    version_info = model_config["version_info"]
    backend_version = version_info["backend_version"]
    tensorlayer_version = version_info["tensorlayer_version"]
    if backend_version != tf.__version__:
        logging.warning(
            "Saved model uses tensorflow version {}, but now you are using tensorflow version {}".format(
                backend_version, tf.__version__
            )
        )
    if tensorlayer_version != tl.__version__:
        logging.warning(
            "Saved model uses tensorlayer version {}, but now you are using tensorlayer version {}".format(
                tensorlayer_version, tl.__version__
            )
        )

    M = static_graph2net(model_config)
    if load_weights:
        if not ('layer_names' in f.attrs.keys()):
            raise RuntimeError("Saved model does not contain weights.")
        M.load_weights(filepath=filepath)

    f.close()

    logging.info("[*] Loaded TL model from {}, loading weights={}".format(filepath, load_weights))

    return M


# def load_pkl_graph(name='model.pkl'):