Using RBF neural networks for testing-CodePudding

I am trying to run this code LINK code on may laptop [LINK CODE][1] , I changed these package:

from keras.engine.topology import Layer
from tensorflow.keras.models import load_model

to these package to work on my machine:

from tensorflow.python.keras.layers import Layer
from tensorflow.python.keras.models import load_model

and whenever I run a program, this part could not be executed:

#model already saved in file
from tensorflow.python.keras.models import  load_model

newmodel1= load_model("Zoghbio.h5",
                          custom_objects={'RBFLayer': RBFLayer})
print("OK")

And I get on this error: How to fix it please?

Traceback (most recent call last):
  File "c:\Users\pc\Desktop\Ali\RBFNetworks\RBF_neural_network_python-master\RBF_neuralNetwork .py", line 214, in <module>
    newmodel1= load_model("Zoghbio.h5",
  File "C:\Users\pc\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\keras\saving\save.py", line 206, in load_model
    return saved_model_load.load(filepath, compile, options)
  File "C:\Users\pc\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\keras\saving\saved_model\load.py", line 122, in load
    meta_graph_def = loader_impl.parse_saved_model(path).meta_graphs[0]
  File "C:\Users\pc\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\saved_model\loader_impl.py", line 115, in parse_saved_model
    raise IOError(
OSError: SavedModel file does not exist at: Zoghbio.h5\{saved_model.pbtxt|saved_model.pb}

UPDATED error:

Save model to file C:/Users/pc/Desktop/RBFNetworks/RBF_neural_network_python-master/my_file.h5 ... Traceback (most recent call last):
  File "c:\Users\pc\Desktop\RBFNetworks\RBF_neural_network_python-master\RBF_neuralNetwork .py", line 214, in <module>
    model.save(z_model)
  File "C:\Users\pc\AppData\Local\Programs\Python\Python38\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "C:\Users\pc\AppData\Local\Programs\Python\Python38\lib\site-packages\keras\engine\base_layer.py", line 745, in get_config
    raise NotImplementedError(textwrap.dedent(f"""
NotImplementedError: 
Layer ModuleWrapper has arguments ['self', 'module', 'method_name']
in `__init__` and therefore must override `get_config()`.

Example:

class CustomLayer(keras.layers.Layer):
    def __init__(self, arg1, arg2):
        super().__init__()
        self.arg1 = arg1
        self.arg2 = arg2

    def get_config(self):
        config = super().get_config()
        config.update({
            "arg1": self.arg1,
            "arg2": self.arg2,
        })
        return config

CodePudding user response：

In the code you linked in another question you have:

# # saving to and loading from file
# z_model = f"Z_model.h5"
# print(f"Save model to file {z_model} ... ", end="")
# model.save(z_model)
# print("OK")

#model already saved in file
from tensorflow.keras.models import  load_model
newmodel1= load_model("Zoghbio.h5", custom_objects={'RBFLayer': RBFLayer})
print("OK")

It is giving you an error because you are trying to load a model that is never saved before. Simply uncomment the portion above:

# saving to and loading from file
z_model = "my_file.h5"
print("Save model to file {} ... ".format(z_model), end="")
model.save(z_model)
print("OK")

# model already saved in file
from tensorflow.keras.models import  load_model
newmodel1= load_model("my_file.h5", custom_objects={'RBFLayer': RBFLayer})
print("OK")

Of course it doesn't makes much sense to train, save and re-load the model right away. I think the author wanted to show how the model could be trained and saved, and then re-loaded avoiding training everything anew. You can load and use the saved model without training each time this way.