AssertionError:

[sauravtii]

Hi, I did add relu activation layer after each conv2d layer and the previous issue did get resolved. I am facing the following issue.

Issue:

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Cell In [13], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:169, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    167 new_mdl['config']['layers'] = layers
    168 new_mdl = json.dumps(new_mdl)
--> 169 new_model = model_from_json(new_mdl,
    170                              custom_objects={'SpikeActivation':SpikeActivation})
    171 input_shape = model.layers[0].input_shape
    172 #new_model.build(input_shape)                            
    173 #new_model = keras.Model(inputs=inputs, outputs=outputs)

File ~/.local/lib/python3.8/site-packages/keras/saving/model_config.py:109, in model_from_json(json_string, custom_objects)
     86 """Parses a JSON model configuration string and returns a model instance.
     87 
     88 Usage:
   (...)
    103     A Keras model instance (uncompiled).
    104 """
    105 from keras.layers import (
    106     deserialize_from_json,
    107 )
--> 109 return deserialize_from_json(json_string, custom_objects=custom_objects)

File ~/.local/lib/python3.8/site-packages/keras/layers/serialization.py:272, in deserialize_from_json(json_string, custom_objects)
    266 populate_deserializable_objects()
    267 config = json_utils.decode_and_deserialize(
    268     json_string,
    269     module_objects=LOCAL.ALL_OBJECTS,
    270     custom_objects=custom_objects,
    271 )
--> 272 return deserialize(config, custom_objects)

File ~/.local/lib/python3.8/site-packages/keras/layers/serialization.py:249, in deserialize(config, custom_objects)
    212 """Instantiates a layer from a config dictionary.
    213 
    214 Args:
   (...)
    246 ```
    247 """
    248 populate_deserializable_objects()
--> 249 return generic_utils.deserialize_keras_object(
    250     config,
    251     module_objects=LOCAL.ALL_OBJECTS,
    252     custom_objects=custom_objects,
    253     printable_module_name="layer",
    254 )

File ~/.local/lib/python3.8/site-packages/keras/utils/generic_utils.py:734, in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    731 custom_objects = custom_objects or {}
    733 if "custom_objects" in arg_spec.args:
--> 734     deserialized_obj = cls.from_config(
    735         cls_config,
    736         custom_objects=dict(
    737             list(_GLOBAL_CUSTOM_OBJECTS.items())
    738             + list(_THREAD_LOCAL_CUSTOM_OBJECTS.__dict__.items())
    739             + list(custom_objects.items())
    740         ),
    741     )
    742 else:
    743     with CustomObjectScope(custom_objects):

File ~/.local/lib/python3.8/site-packages/keras/engine/training.py:3034, in Model.from_config(cls, config, custom_objects)
   3027 functional_model_keys = [
   3028     "name",
   3029     "layers",
   3030     "input_layers",
   3031     "output_layers",
   3032 ]
   3033 if all(key in config for key in functional_model_keys):
-> 3034     inputs, outputs, layers = functional.reconstruct_from_config(
   3035         config, custom_objects
   3036     )
   3037     model = cls(
   3038         inputs=inputs, outputs=outputs, name=config.get("name")
   3039     )
   3040     functional.connect_ancillary_layers(model, layers)

File ~/.local/lib/python3.8/site-packages/keras/engine/functional.py:1510, in reconstruct_from_config(config, custom_objects, created_layers)
   1508 for layer_data in tf.nest.flatten(output_layers):
   1509     layer_name, node_index, tensor_index = layer_data.as_list()
-> 1510     assert layer_name in created_layers
   1511     layer = created_layers[layer_name]
   1512     node_index = get_node_index(layer, node_index)

AssertionError: 

My model architecture:

input_shape = (32, 32, 3)
input_layer = Input(input_shape)

layer = Conv2D(filters=4,
               kernel_size=(1, 1),
               strides=(1, 1),
               padding="same")(input_layer)

layer=Activation('relu')(layer)

# 1
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(input_layer)

layer=Activation('relu')(layer)

# 2
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 3
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 4
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 5
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 6
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 7
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 8
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 9
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 10
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 11
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 12
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 13
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

layer = Flatten()(layer)

layer = Dense(units=512)(layer)

layer=Activation('relu')(layer)

layer = Dense(units=10)(layer)

layer=Activation('relu')(layer)

model = Model(input_layer, layer)

My model summary:

Model: "model"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_1 (InputLayer)        [(None, 32, 32, 3)]       0         

 conv2d_1 (Conv2D)           (None, 32, 32, 64)        1792      

 activation_1 (Activation)   (None, 32, 32, 64)        0         

 conv2d_2 (Conv2D)           (None, 32, 32, 64)        36928     

 activation_2 (Activation)   (None, 32, 32, 64)        0         

 conv2d_3 (Conv2D)           (None, 16, 16, 64)        36928     

 activation_3 (Activation)   (None, 16, 16, 64)        0         

 conv2d_4 (Conv2D)           (None, 16, 16, 128)       73856     

 activation_4 (Activation)   (None, 16, 16, 128)       0         

 conv2d_5 (Conv2D)           (None, 16, 16, 128)       147584    

 activation_5 (Activation)   (None, 16, 16, 128)       0         

 conv2d_6 (Conv2D)           (None, 8, 8, 128)         147584    

 activation_6 (Activation)   (None, 8, 8, 128)         0         

 conv2d_7 (Conv2D)           (None, 8, 8, 256)         295168    

 activation_7 (Activation)   (None, 8, 8, 256)         0         

 conv2d_8 (Conv2D)           (None, 8, 8, 256)         590080    

 activation_8 (Activation)   (None, 8, 8, 256)         0         

 conv2d_9 (Conv2D)           (None, 8, 8, 256)         590080    

 activation_9 (Activation)   (None, 8, 8, 256)         0         

 conv2d_10 (Conv2D)          (None, 4, 4, 256)         590080    

 activation_10 (Activation)  (None, 4, 4, 256)         0         

 conv2d_11 (Conv2D)          (None, 4, 4, 512)         1180160   

 activation_11 (Activation)  (None, 4, 4, 512)         0         

 conv2d_12 (Conv2D)          (None, 4, 4, 512)         2359808   

 activation_12 (Activation)  (None, 4, 4, 512)         0         

 conv2d_13 (Conv2D)          (None, 4, 4, 512)         2359808   

 activation_13 (Activation)  (None, 4, 4, 512)         0         

 conv2d_14 (Conv2D)          (None, 2, 2, 512)         2359808   

 activation_14 (Activation)  (None, 2, 2, 512)         0         

 conv2d_15 (Conv2D)          (None, 2, 2, 512)         2359808   

 activation_15 (Activation)  (None, 2, 2, 512)         0         

 conv2d_16 (Conv2D)          (None, 2, 2, 512)         2359808   

 activation_16 (Activation)  (None, 2, 2, 512)         0         

 conv2d_17 (Conv2D)          (None, 2, 2, 512)         2359808   

 activation_17 (Activation)  (None, 2, 2, 512)         0         

 conv2d_18 (Conv2D)          (None, 1, 1, 512)         2359808   

 activation_18 (Activation)  (None, 1, 1, 512)         0         

 flatten (Flatten)           (None, 512)               0         

 dense (Dense)               (None, 512)               262656    

 activation_19 (Activation)  (None, 512)               0         

 dense_1 (Dense)             (None, 10)                5130      

 activation_20 (Activation)  (None, 10)                0         

=================================================================
Total params: 20,476,682
Trainable params: 20,476,682
Non-trainable params: 0
_________________________________________________________________

[Dengyu-Wu]

Can you replace the last activation layer by,

• layer=Activation('softmax')(layer)

and see if it helps?

[sauravtii]

It didn't, facing the same error again.

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Cell In [12], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:169, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    167 new_mdl['config']['layers'] = layers
    168 new_mdl = json.dumps(new_mdl)
--> 169 new_model = model_from_json(new_mdl,
    170                              custom_objects={'SpikeActivation':SpikeActivation})
    171 input_shape = model.layers[0].input_shape
    172 #new_model.build(input_shape)                            
    173 #new_model = keras.Model(inputs=inputs, outputs=outputs)

File ~/.local/lib/python3.8/site-packages/keras/saving/model_config.py:109, in model_from_json(json_string, custom_objects)
     86 """Parses a JSON model configuration string and returns a model instance.
     87 
     88 Usage:
   (...)
    103     A Keras model instance (uncompiled).
    104 """
    105 from keras.layers import (
    106     deserialize_from_json,
    107 )
--> 109 return deserialize_from_json(json_string, custom_objects=custom_objects)

File ~/.local/lib/python3.8/site-packages/keras/layers/serialization.py:272, in deserialize_from_json(json_string, custom_objects)
    266 populate_deserializable_objects()
    267 config = json_utils.decode_and_deserialize(
    268     json_string,
    269     module_objects=LOCAL.ALL_OBJECTS,
    270     custom_objects=custom_objects,
    271 )
--> 272 return deserialize(config, custom_objects)

File ~/.local/lib/python3.8/site-packages/keras/layers/serialization.py:249, in deserialize(config, custom_objects)
    212 """Instantiates a layer from a config dictionary.
    213 
    214 Args:
   (...)
    246 ```
    247 """
    248 populate_deserializable_objects()
--> 249 return generic_utils.deserialize_keras_object(
    250     config,
    251     module_objects=LOCAL.ALL_OBJECTS,
    252     custom_objects=custom_objects,
    253     printable_module_name="layer",
    254 )

File ~/.local/lib/python3.8/site-packages/keras/utils/generic_utils.py:734, in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    731 custom_objects = custom_objects or {}
    733 if "custom_objects" in arg_spec.args:
--> 734     deserialized_obj = cls.from_config(
    735         cls_config,
    736         custom_objects=dict(
    737             list(_GLOBAL_CUSTOM_OBJECTS.items())
    738             + list(_THREAD_LOCAL_CUSTOM_OBJECTS.__dict__.items())
    739             + list(custom_objects.items())
    740         ),
    741     )
    742 else:
    743     with CustomObjectScope(custom_objects):

File ~/.local/lib/python3.8/site-packages/keras/engine/training.py:3034, in Model.from_config(cls, config, custom_objects)
   3027 functional_model_keys = [
   3028     "name",
   3029     "layers",
   3030     "input_layers",
   3031     "output_layers",
   3032 ]
   3033 if all(key in config for key in functional_model_keys):
-> 3034     inputs, outputs, layers = functional.reconstruct_from_config(
   3035         config, custom_objects
   3036     )
   3037     model = cls(
   3038         inputs=inputs, outputs=outputs, name=config.get("name")
   3039     )
   3040     functional.connect_ancillary_layers(model, layers)

File ~/.local/lib/python3.8/site-packages/keras/engine/functional.py:1510, in reconstruct_from_config(config, custom_objects, created_layers)
   1508 for layer_data in tf.nest.flatten(output_layers):
   1509     layer_name, node_index, tensor_index = layer_data.as_list()
-> 1510     assert layer_name in created_layers
   1511     layer = created_layers[layer_name]
   1512     node_index = get_node_index(layer, node_index)

AssertionError: 

Model architecture:

input_shape = (32, 32, 3)
input_layer = Input(input_shape)

layer = Conv2D(filters=4,
               kernel_size=(1, 1),
               strides=(1, 1),
               padding="same")(input_layer)

layer=Activation('relu')(layer)

# 1
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(input_layer)

layer=Activation('relu')(layer)

# 2
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=64,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 3
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 4
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=128,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 5
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 6
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 7
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=256,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 8
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 9
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 10
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 11
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 12
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# 13
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(1, 1),
               padding="same")(layer)

layer=Activation('relu')(layer)

# Using Conv layer as a pooling layer
layer = Conv2D(filters=512,
               kernel_size=(3, 3),
               strides=(2, 2),
               padding="same")(layer)

layer=Activation('relu')(layer)

layer = Flatten()(layer)

layer = Dense(units=512)(layer)

layer=Activation('relu')(layer)

layer = Dense(units=10)(layer)

layer=Activation('Softmax')(layer)

model = Model(input_layer, layer)

[Dengyu-Wu]

What's the tensorflow version you using?

[sauravtii]

2.10.0

[Dengyu-Wu]

You may need downgrade the version.

SpKeras was originally tested in tensorflow 2.3.1. I also tested it with version below 2.5 and it works fine.

[sauravtii]

I did downgrade the tensorflow version to 2.3.1 but facing the same issue:

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Cell In [16], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:169, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    167 new_mdl['config']['layers'] = layers
    168 new_mdl = json.dumps(new_mdl)
--> 169 new_model = model_from_json(new_mdl,
    170                              custom_objects={'SpikeActivation':SpikeActivation})
    171 input_shape = model.layers[0].input_shape
    172 #new_model.build(input_shape)                            
    173 #new_model = keras.Model(inputs=inputs, outputs=outputs)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py:122, in model_from_json(json_string, custom_objects)
    120 config = json.loads(json_string)
    121 from tensorflow.python.keras.layers import deserialize  # pylint: disable=g-import-not-at-top
--> 122 return deserialize(config, custom_objects=custom_objects)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py:171, in deserialize(config, custom_objects)
    160 """Instantiates a layer from a config dictionary.
    161 
    162 Arguments:
   (...)
    168     Layer instance (may be Model, Sequential, Network, Layer...)
    169 """
    170 populate_deserializable_objects()
--> 171 return generic_utils.deserialize_keras_object(
    172     config,
    173     module_objects=LOCAL.ALL_OBJECTS,
    174     custom_objects=custom_objects,
    175     printable_module_name='layer')

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py:354, in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    351 custom_objects = custom_objects or {}
    353 if 'custom_objects' in arg_spec.args:
--> 354   return cls.from_config(
    355       cls_config,
    356       custom_objects=dict(
    357           list(_GLOBAL_CUSTOM_OBJECTS.items()) +
    358           list(custom_objects.items())))
    359 with CustomObjectScope(custom_objects):
    360   return cls.from_config(cls_config)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:616, in Functional.from_config(cls, config, custom_objects)
    600 @classmethod
    601 def from_config(cls, config, custom_objects=None):
    602   """Instantiates a Model from its config (output of `get_config()`).
    603 
    604   Arguments:
   (...)
    614       ValueError: In case of improperly formatted config dict.
    615   """
--> 616   input_tensors, output_tensors, created_layers = reconstruct_from_config(
    617       config, custom_objects)
    618   model = cls(inputs=input_tensors, outputs=output_tensors,
    619               name=config.get('name'))
    620   connect_ancillary_layers(model, created_layers)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:1233, in reconstruct_from_config(config, custom_objects, created_layers)
   1231 for layer_data in nest.flatten(output_layers):
   1232   layer_name, node_index, tensor_index = layer_data.as_list()
-> 1233   assert layer_name in created_layers
   1234   layer = created_layers[layer_name]
   1235   node_index = get_node_index(layer, node_index)

AssertionError: 

[Dengyu-Wu]

It could be caused by the version problem, but I cannot reproduce your error.

The package works fine to me, when I followed the setup, tensorflow 2.3.1 and python 3.7.6.

[sauravtii]

I have a python version greater that 3.7.6. But I don't think that might be the problem.

[sauravtii]

This is my code: spkeras_vgg16.zip

[Dengyu-Wu]

import sys
print(sys.version)
print(tf.__version__)
--------------------------
3.8.8 (default, Apr 13 2021, 19:58:26) 
[GCC 7.3.0]
2.5.0

I tested your code under the above environment, it works well.

[sauravtii]

I tried with tensorflow 2.5.0 and got the same error again. Below I have attached the entire output along with the error.

2022-11-24 13:55:56.577963: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-11-24 13:55:56.577982: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
/usr/lib/python3/dist-packages/requests/__init__.py:89: RequestsDependencyWarning: urllib3 (1.26.12) or chardet (3.0.4) doesn't match a supported version!
  warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
3.8.10 (default, Jun 22 2022, 20:18:18) 
[GCC 9.4.0]
2.5.0
2022-11-24 13:55:57.683418: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
/usr/lib/python3/dist-packages/requests/__init__.py:89: RequestsDependencyWarning: urllib3 (1.26.12) or chardet (3.0.4) doesn't match a supported version!
  warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
2022-11-24 13:55:58.366131: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366179: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublas.so.11'; dlerror: libcublas.so.11: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366206: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublasLt.so.11'; dlerror: libcublasLt.so.11: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366233: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcufft.so.10'; dlerror: libcufft.so.10: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366259: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcurand.so.10'; dlerror: libcurand.so.10: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366286: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366312: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusparse.so.11'; dlerror: libcusparse.so.11: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366339: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory
2022-11-24 13:55:58.366345: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1766] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2022-11-24 13:55:58.572707: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcuda.so.1
2022-11-24 13:55:58.574715: E tensorflow/stream_executor/cuda/cuda_driver.cc:328] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2022-11-24 13:55:58.574733: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: TII-SPAWAR01
2022-11-24 13:55:58.574737: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: TII-SPAWAR01
2022-11-24 13:55:58.574797: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 515.65.1
2022-11-24 13:55:58.574811: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 515.65.1
2022-11-24 13:55:58.574814: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 515.65.1
[]
2.5.0
2022-11-24 13:55:59.133046: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 32, 32, 3)]       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 32, 32, 64)        1792      
_________________________________________________________________
activation_1 (Activation)    (None, 32, 32, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 32, 32, 64)        36928     
_________________________________________________________________
activation_2 (Activation)    (None, 32, 32, 64)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 16, 16, 64)        36928     
_________________________________________________________________
activation_3 (Activation)    (None, 16, 16, 64)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 16, 16, 128)       73856     
_________________________________________________________________
activation_4 (Activation)    (None, 16, 16, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 16, 16, 128)       147584    
_________________________________________________________________
activation_5 (Activation)    (None, 16, 16, 128)       0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 8, 8, 128)         147584    
_________________________________________________________________
activation_6 (Activation)    (None, 8, 8, 128)         0         
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 8, 8, 256)         295168    
_________________________________________________________________
activation_7 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 8, 8, 256)         590080    
_________________________________________________________________
activation_8 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 8, 8, 256)         590080    
_________________________________________________________________
activation_9 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 4, 4, 256)         590080    
_________________________________________________________________
activation_10 (Activation)   (None, 4, 4, 256)         0         
_________________________________________________________________
conv2d_11 (Conv2D)           (None, 4, 4, 512)         1180160   
_________________________________________________________________
activation_11 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_12 (Conv2D)           (None, 4, 4, 512)         2359808   
_________________________________________________________________
activation_12 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 4, 4, 512)         2359808   
_________________________________________________________________
activation_13 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_14 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_14 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_15 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_15 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_16 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_16 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_17 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_17 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_18 (Conv2D)           (None, 1, 1, 512)         2359808   
_________________________________________________________________
activation_18 (Activation)   (None, 1, 1, 512)         0         
_________________________________________________________________
flatten (Flatten)            (None, 512)               0         
_________________________________________________________________
dense (Dense)                (None, 512)               262656    
_________________________________________________________________
activation_19 (Activation)   (None, 512)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 10)                5130      
_________________________________________________________________
activation_20 (Activation)   (None, 10)                0         
=================================================================
Total params: 20,476,682
Trainable params: 20,476,682
Non-trainable params: 0
_________________________________________________________________
2022-11-24 13:55:59.741497: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)
2022-11-24 13:55:59.759633: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 2496000000 Hz
1407/1407 [==============================] - 725s 515ms/step - loss: 4.7958 - accuracy: 0.1483 - val_loss: 4.7171 - val_accuracy: 0.1804
313/313 [==============================] - 17s 53ms/step - loss: 4.6982 - accuracy: 0.1789
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 32, 32, 3)]       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 32, 32, 64)        1792      
_________________________________________________________________
activation_1 (Activation)    (None, 32, 32, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 32, 32, 64)        36928     
_________________________________________________________________
activation_2 (Activation)    (None, 32, 32, 64)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 16, 16, 64)        36928     
_________________________________________________________________
activation_3 (Activation)    (None, 16, 16, 64)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 16, 16, 128)       73856     
_________________________________________________________________
activation_4 (Activation)    (None, 16, 16, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 16, 16, 128)       147584    
_________________________________________________________________
activation_5 (Activation)    (None, 16, 16, 128)       0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 8, 8, 128)         147584    
_________________________________________________________________
activation_6 (Activation)    (None, 8, 8, 128)         0         
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 8, 8, 256)         295168    
_________________________________________________________________
activation_7 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 8, 8, 256)         590080    
_________________________________________________________________
activation_8 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 8, 8, 256)         590080    
_________________________________________________________________
activation_9 (Activation)    (None, 8, 8, 256)         0         
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 4, 4, 256)         590080    
_________________________________________________________________
activation_10 (Activation)   (None, 4, 4, 256)         0         
_________________________________________________________________
conv2d_11 (Conv2D)           (None, 4, 4, 512)         1180160   
_________________________________________________________________
activation_11 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_12 (Conv2D)           (None, 4, 4, 512)         2359808   
_________________________________________________________________
activation_12 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 4, 4, 512)         2359808   
_________________________________________________________________
activation_13 (Activation)   (None, 4, 4, 512)         0         
_________________________________________________________________
conv2d_14 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_14 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_15 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_15 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_16 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_16 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_17 (Conv2D)           (None, 2, 2, 512)         2359808   
_________________________________________________________________
activation_17 (Activation)   (None, 2, 2, 512)         0         
_________________________________________________________________
conv2d_18 (Conv2D)           (None, 1, 1, 512)         2359808   
_________________________________________________________________
activation_18 (Activation)   (None, 1, 1, 512)         0         
_________________________________________________________________
flatten (Flatten)            (None, 512)               0         
_________________________________________________________________
dense (Dense)                (None, 512)               262656    
_________________________________________________________________
activation_19 (Activation)   (None, 512)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 10)                5130      
_________________________________________________________________
activation_20 (Activation)   (None, 10)                0         
=================================================================
Total params: 20,476,682
Trainable params: 20,476,682
Non-trainable params: 0
_________________________________________________________________
{'timesteps': 256, 'thresholding': 0.5, 'amp_factor': 100, 'signed_bit': 0, 'spike_ext': 0, 'epsilon': 0.001, 'use_bias': True, 'scaling_factor': 1, 'noneloss': False, 'method': 1}
Start Converting...
Extracting Lambda...
2/42Activation
4/42Activation
6/42Activation
8/42Activation
10/42Activation
12/42Activation
14/42Activation
16/42Activation
18/42Activation
20/42Activation
22/42Activation
24/42Activation
26/42Activation
28/42Activation
30/42Activation
32/42Activation
34/42Activation
36/42Activation
39/42Activation
41/42Activation
maximum activations: [1.0, 0.5849826, 0.42816296, 0.5129265, 0.8821699, 0.8865767, 0.9058886, 0.74633074, 1.1824455, 0.86154443, 1.7145554, 1.345744, 1.9324017, 11.691247, 7.8629975, 10.439115, 7.9022923, 10.038851, 23.341845, 31.82572, 71.77048]
normalisation factor: [0.5849826, 0.7319243, 1.1979703, 1.7198758, 1.0049955, 1.0217825, 0.8238659, 1.5843452, 0.72861236, 1.9900951, 0.7848939, 1.4359355, 6.0501122, 0.6725542, 1.3276253, 0.75698876, 1.270372, 2.325151, 1.3634621, 2.2551093]
Number of Spiking Layer: 20
threshold: [100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100, 100]
Note: threshold will be different when weight quantisation applied!
Traceback (most recent call last):
  File "spkeras_vgg16 (1).py", line 325, in <module>
    snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)
  File "/home/sauravpawar/Downloads/spkeras/spkeras/models.py", line 29, in __call__
    self.model = self.convert(mdl,x_train,                    
  File "/home/sauravpawar/Downloads/spkeras/spkeras/models.py", line 169, in convert
    new_model = model_from_json(new_mdl,
  File "/home/sauravpawar/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py", line 126, in model_from_json
    return deserialize(config, custom_objects=custom_objects)
  File "/home/sauravpawar/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py", line 159, in deserialize
    return generic_utils.deserialize_keras_object(
  File "/home/sauravpawar/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 668, in deserialize_keras_object
    deserialized_obj = cls.from_config(
  File "/home/sauravpawar/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py", line 668, in from_config
    input_tensors, output_tensors, created_layers = reconstruct_from_config(
  File "/home/sauravpawar/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py", line 1308, in reconstruct_from_config
    assert layer_name in created_layers
AssertionError

[Dengyu-Wu]

It seems your tensorflow is not working properly. You need solve the missing files first before you moving to SpKeras.

2022-11-24 13:55:56.577963: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory

[sauravtii]

I did resolve that issue but again getting the same error. Below I have attached the full output.

Resolved tensorflow issues:

AssertionError:

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Cell In [15], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:169, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    167 new_mdl['config']['layers'] = layers
    168 new_mdl = json.dumps(new_mdl)
--> 169 new_model = model_from_json(new_mdl,
    170                              custom_objects={'SpikeActivation':SpikeActivation})
    171 input_shape = model.layers[0].input_shape
    172 #new_model.build(input_shape)                            
    173 #new_model = keras.Model(inputs=inputs, outputs=outputs)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py:126, in model_from_json(json_string, custom_objects)
    124 config = json_utils.decode(json_string)
    125 from tensorflow.python.keras.layers import deserialize  # pylint: disable=g-import-not-at-top
--> 126 return deserialize(config, custom_objects=custom_objects)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py:159, in deserialize(config, custom_objects)
    148 """Instantiates a layer from a config dictionary.
    149 
    150 Args:
   (...)
    156     Layer instance (may be Model, Sequential, Network, Layer...)
    157 """
    158 populate_deserializable_objects()
--> 159 return generic_utils.deserialize_keras_object(
    160     config,
    161     module_objects=LOCAL.ALL_OBJECTS,
    162     custom_objects=custom_objects,
    163     printable_module_name='layer')

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py:668, in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
    665 custom_objects = custom_objects or {}
    667 if 'custom_objects' in arg_spec.args:
--> 668   deserialized_obj = cls.from_config(
    669       cls_config,
    670       custom_objects=dict(
    671           list(_GLOBAL_CUSTOM_OBJECTS.items()) +
    672           list(custom_objects.items())))
    673 else:
    674   with CustomObjectScope(custom_objects):

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:668, in Functional.from_config(cls, config, custom_objects)
    653 """Instantiates a Model from its config (output of `get_config()`).
    654 
    655 Args:
   (...)
    665     ValueError: In case of improperly formatted config dict.
    666 """
    667 with generic_utils.SharedObjectLoadingScope():
--> 668   input_tensors, output_tensors, created_layers = reconstruct_from_config(
    669       config, custom_objects)
    670   model = cls(inputs=input_tensors, outputs=output_tensors,
    671               name=config.get('name'))
    672   connect_ancillary_layers(model, created_layers)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:1308, in reconstruct_from_config(config, custom_objects, created_layers)
   1306 for layer_data in nest.flatten(output_layers):
   1307   layer_name, node_index, tensor_index = layer_data.as_list()
-> 1308   assert layer_name in created_layers
   1309   layer = created_layers[layer_name]
   1310   node_index = get_node_index(layer, node_index)

AssertionError: 

[Dengyu-Wu]

It could be caused by your last layer which is not softmax.

I have updated models.py to fix the problem.

[sauravtii]

Hi, thanks for the updating models.py. The previous error has been resolved, but now getting a NameError.

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In [18], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:179, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    175 #new_model.build(input_shape)                            
    176 #new_model = keras.Model(inputs=inputs, outputs=outputs)
    178 m = 0
--> 179 for layer in new_model.layers:
    180     layer_type = type(layer).__name__ 
    181     if hasattr(layer, 'activation') and layer_type != 'Activation':

NameError: name 'new_model' is not defined

[Dengyu-Wu]

Did you update your code correctly? new_model is defined in L171.

https://github.com/Dengyu-Wu/spkeras/blob/master/spkeras/models.py#L171

[sauravtii]

I did make the necessary changes and was able to resolve that issue. But now facing the following issue:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In [17], line 7
      2 from spkeras.spkeras.models import cnn_to_snn
      4 #Current normalisation using cnn_to_snn
      5 ##Default: signed_bit=0, amp_factor=100, method=1, epsilon = 0.001
----> 7 snn_model = cnn_to_snn(signed_bit=0)(cnn_model,x_train)

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:29, in cnn_to_snn.__call__(self, mdl, x_train)
     27 self.use_bias = use_bias        
     28 self.get_config()
---> 29 self.model = self.convert(mdl,x_train,                    
     30                           thresholding = self.thresholding,
     31                           scaling_factor = self.scaling_factor,
     32                           method = self.method,
     33                           timesteps=self.timesteps)
     35 return self

File /opt/ml_team_data/saurav/new/saurav/vgg16/SpKeras/spkeras/spkeras/models.py:173, in cnn_to_snn.convert(self, mdl, x_train, thresholding, scaling_factor, method, timesteps)
    170 new_mdl['config']['output_layers'] =  [[inbound_nodes, 0, 0]]        
    172 # new_mdl = json.dumps(new_mdl)
--> 173 new_model = model_from_json(new_mdl,custom_objects={'SpikeActivation':SpikeActivation})
    174 input_shape = model.layers[0].input_shape
    175 #new_model.build(input_shape)                            
    176 #new_model = keras.Model(inputs=inputs, outputs=outputs)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py:124, in model_from_json(json_string, custom_objects)
    103 @keras_export('keras.models.model_from_json')
    104 def model_from_json(json_string, custom_objects=None):
    105   """Parses a JSON model configuration string and returns a model instance.
    106 
    107   Usage:
   (...)
    122       A Keras model instance (uncompiled).
    123   """
--> 124   config = json_utils.decode(json_string)
    125   from tensorflow.python.keras.layers import deserialize  # pylint: disable=g-import-not-at-top
    126   return deserialize(config, custom_objects=custom_objects)

File ~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/json_utils.py:62, in decode(json_string)
     61 def decode(json_string):
---> 62   return json.loads(json_string, object_hook=_decode_helper)

File /opt/conda/envs/test/lib/python3.8/json/__init__.py:341, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
    339 else:
    340     if not isinstance(s, (bytes, bytearray)):
--> 341         raise TypeError(f'the JSON object must be str, bytes or bytearray, '
    342                         f'not {s.__class__.__name__}')
    343     s = s.decode(detect_encoding(s), 'surrogatepass')
    345 if "encoding" in kw:

TypeError: the JSON object must be str, bytes or bytearray, not dict

[Dengyu-Wu]

Can you try the exactly same code as I updated, see if it works?

[Dengyu-Wu]

AssertionError is fixed in updated code, so the issue is closed.