TypeError: Unrecognized keyword arguments: ['batch_shape'] when loading a Keras model

Question

I'm working on a face recognition project where I trained a model using TensorFlow/Keras and saved it as face_recog_vggface.h5. While attempting to load the model using tf.keras.models.load_model(), I encounter the following error:

TypeError                                 Traceback (most recent call last)
Cell In[20], line 3
      1 # Load the trained model
      2 model_path = 'face_recog_vggface.h5'
----> 3 model = tf.keras.models.load_model(model_path, custom_objects={'triplet_loss': triplet_loss_function})

File ~/.local/lib/python3.8/site-packages/keras/src/saving/saving_api.py:238, in load_model(filepath, custom_objects, compile, safe_mode, **kwargs)
    230     return saving_lib.load_model(
    231         filepath,
    232         custom_objects=custom_objects,
    233         compile=compile,
    234         safe_mode=safe_mode,
    235     )
    237 # Legacy case.
--> 238 return legacy_sm_saving_lib.load_model(
    239     filepath, custom_objects=custom_objects, compile=compile, **kwargs
    240 )

File ~/.local/lib/python3.8/site-packages/keras/src/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     67     filtered_tb = _process_traceback_frames(e.__traceback__)
     68     # To get the full stack trace, call:
     69     # `tf.debugging.disable_traceback_filtering()`
---> 70     raise e.with_traceback(filtered_tb) from None
     71 finally:
     72     del filtered_tb

File ~/.local/lib/python3.8/site-packages/keras/src/engine/base_layer.py:870, in Layer.from_config(cls, config)
    868     return cls(**config)
    869 except Exception as e:
--> 870     raise TypeError(
    871         f"Error when deserializing class '{cls.__name__}' using "
    872         f"config={config}.\n\nException encountered: {e}"
    873     )

TypeError: Error when deserializing class 'InputLayer' using config={'batch_shape': [None, 224, 224, 3], 'dtype': 'float32', 'sparse': False, 'name': 'input_layer'}.

Exception encountered: Unrecognized keyword arguments: ['batch_shape']

# Model Definition
from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.keras.models import Model
from tensorflow.keras.layers import GlobalAveragePooling2D, Dense

def build_model():
    base_model = VGG16(include_top=False, input_shape=(224, 224, 3))
    x = base_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(128, activation='relu')(x)
    model = Model(inputs=base_model.input, outputs=x)
    return model

model = build_model()
model.save('face_recog_vggface.h5')

# Model Loading
from tensorflow.keras.models import load_model
model = load_model('face_recog_vggface.h5', custom_objects={'triplet_loss': triplet_loss})

I saved the model after training it as face_recog_vggface.h5 and it shows the error as seen above when I try loading it why? I used tensorflow==2.13 to load it same with the version of keras, which is still 2.13.

Answer 1

This might not be the best solution, but it addresses your issue. The problem seems to stem from compatibility between versions. Here’s a workaround that worked for me:

Instead of loading the entire model, try loading just its weights:

model.load_weights(<weights_path>)