datos de carga de tensorflow: datos marshal incorrectos

Question

Quiero cargar FaceNet en Keras pero recibo errores. el modal facenet_keras.h5 está listo pero no puedo cargarlo.

puede obtener facenet_keras.h5 desde este enlace:

https://drive.google.com/drive/folders/1pwQ3H4aJ8a6yyJHZkTwtjcL4wYWQb7bn

Mi versión de tensorflow es:

tensorflow.__version__

"2.2.0"

y cuando quiero cargar datos:

from tensorflow.keras.models import load_model
load_model('facenet_keras.h5')

obtener este error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-6-2a20f38e8217> in <module>
----> 1 load_model('facenet_keras.h5')

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/save.py in load_model(filepath, custom_objects, compile)
    182     if (h5py is not None and (
    183         isinstance(filepath, h5py.File) or h5py.is_hdf5(filepath))):
--> 184       return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
    185 
    186     if sys.version_info >= (3, 4) and isinstance(filepath, pathlib.Path):

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/hdf5_format.py in load_model_from_hdf5(filepath, custom_objects, compile)
    175       raise ValueError('No model found in config file.')
    176     model_config = json.loads(model_config.decode('utf-8'))
--> 177     model = model_config_lib.model_from_config(model_config,
    178                                                custom_objects=custom_objects)
    179 

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py in model_from_config(config, custom_objects)
     53                     '`Sequential.from_config(config)`?')
     54   from tensorflow.python.keras.layers import deserialize  # pylint: disable=g-import-not-at-top
---> 55   return deserialize(config, custom_objects=custom_objects)
     56 
     57 

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py in deserialize(config, custom_objects)
    103     config['class_name'] = _DESERIALIZATION_TABLE[layer_class_name]
    104 
--> 105   return deserialize_keras_object(
    106       config,
    107       module_objects=globs,

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    367 
    368       if 'custom_objects' in arg_spec.args:
--> 369         return cls.from_config(
    370             cls_config,
    371             custom_objects=dict(

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in from_config(cls, config, custom_objects)
    984         ValueError: In case of improperly formatted config dict.
    985     """
--> 986     input_tensors, output_tensors, created_layers = reconstruct_from_config(
    987         config, custom_objects)
    988     model = cls(inputs=input_tensors, outputs=output_tensors,

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in reconstruct_from_config(config, custom_objects, created_layers)
   2017   # First, we create all layers and enqueue nodes to be processed
   2018   for layer_data in config['layers']:
-> 2019     process_layer(layer_data)
   2020   # Then we process nodes in order of layer depth.
   2021   # Nodes that cannot yet be processed (if the inbound node

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in process_layer(layer_data)
   1999       from tensorflow.python.keras.layers import deserialize as deserialize_layer  # pylint: disable=g-import-not-at-top
   2000 
-> 2001       layer = deserialize_layer(layer_data, custom_objects=custom_objects)
   2002       created_layers[layer_name] = layer
   2003 

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py in deserialize(config, custom_objects)
    103     config['class_name'] = _DESERIALIZATION_TABLE[layer_class_name]
    104 
--> 105   return deserialize_keras_object(
    106       config,
    107       module_objects=globs,

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    367 
    368       if 'custom_objects' in arg_spec.args:
--> 369         return cls.from_config(
    370             cls_config,
    371             custom_objects=dict(

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py in from_config(cls, config, custom_objects)
    988   def from_config(cls, config, custom_objects=None):
    989     config = config.copy()
--> 990     function = cls._parse_function_from_config(
    991         config, custom_objects, 'function', 'module', 'function_type')
    992 

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py in _parse_function_from_config(cls, config, custom_objects, func_attr_name, module_attr_name, func_type_attr_name)
   1040     elif function_type == 'lambda':
   1041       # Unsafe deserialization from bytecode
-> 1042       function = generic_utils.func_load(
   1043           config[func_attr_name], globs=globs)
   1044     elif function_type == 'raw':

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in func_load(code, defaults, closure, globs)
    469   except (UnicodeEncodeError, binascii.Error):
    470     raw_code = code.encode('raw_unicode_escape')
--> 471   code = marshal.loads(raw_code)
    472   if globs is None:
    473     globs = globals()

ValueError: bad marshal data (unknown type code)

gracias.

Answer 1

Las posibles soluciones a este error se muestran a continuación:

1. Es Modelposible que se haya creado y guardado, Python 2.xy es posible que esté utilizando Python 3.x. La solución es utilizar el mismo Python Versionque Modelha sido Builty Saved.

2. Utilice la misma versión de Keras(y, puede ser, tensorflow), en la que estaba su modelo Builty Saved.

3. El Saved Modelprograma podría contener objetos personalizados. Si es así, debe cargar el modelo usando el código,

   new_model = tf.keras.models.load_model('model.h5', custom_objects={'CustomLayer': CustomLayer})

4. Si puede recrear el architecture(es decir, tiene el código original usado para generarlo), puede crear una instancia modelde ese código y luego usarlo model.load_weights('your_model_file.hdf5')para cargar los pesos. Esta no es una opción si no tiene el código utilizado para crear el original architecture.

Para obtener más detalles, consulte este problema de Github . Para obtener más detalles sobre Saving and Loading the Modelcon Custom Objects, consulte esta Documentación de Tensorflow y esta Respuesta de Stack Overflow .