Keras using Google Collaboration cannot model.save

I'm learning image recognition through a book called Image Recognition Programming Recipe.
When I try to save the model in keras, an error occurs and I cannot save it.
I thought the following site might be helpful, but I couldn't understand it well even after reading it.

Try to model.save in Keras and getoverrideget_configWhat to do with the error

Due to the number of characters, we have extracted some of the models.
Please let me know if you need any information.

Model

model=Sequential()

# decide how to learn

# (Learning style, loss function, evaluation method of correctness)
model.compile(optimizer=keras.optimizers.Adadelta(),
            loss=keras.losses.categorical_crossentropy,
            metrics=["accuracy"])

print("Repeated Learning Count:",EPOCHS)
fit_record=model.fit(train_data,train_teacher_labels,batch_size=BATCH_SIZE,epochs=EPOCHS, verbose=1,validation_data=(test_data,test_teacher_labels))

# building neural networks

# Convolution layer (number of neurons in input, width and height of convolution area, activation function, format of input data)
model.add(Conv2D(32, kernel_size=(3,3), activation="relu", input_shape=input_shape))
model.add(Conv2D(64,(3,3), activation="relu"))
# pooling layer
model.add(MaxPooling2D(pool_size=(2,2))))
# Dropout layer (prevent overlearning)
model.add (Dropout (0.25))
#smooth the input
model.add(Flatten())
# Full bond layer (128 nodes, activation function)
model.add(Dense(128, activation="relu"))
model.add(Dropout(0.5))
# Output layer (numbers num_classes)
model.add(Dense(NUM_CLASSES, activation="softmax"))

When I got an error

model.save("keras-mnist-model.h5")

Error Contents

NotImplementedError Traceback (most recent call last)
<ipython-input-90-a2ac93d46f7c>in<module>()
---->1model.save("keras-mnist-model.h5")

8 frames
/usr/local/lib/python 3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py inget_config(self)
    719 raise NotImplementedError('Layer%shas arguments in `__init__`and'
    720'therefore must override`get_config`.'%
-->721self.__class__.__name__)
    722 return config
    723 

NotImplementedError: Layer ModuleWrapper has arguments in `__init__` and therefore must override`get_config`.

keras 2.5.0
tensorflow 2.5.0
numpy1.19.5
macOSX
Google colab

python machine-learning tensorflow keras google-colaboratory

2022-09-30 16:24

1 Answers

Consider MNIST as an example:

model after creating the architecture
Training the model (call the fit method) should be done after creating an architecture and compiling.
Verify that the shape of the data is correct.

import numpy as np
from tensorflow import keras
from tensorflow.keras.layers import*
from tensorflow.keras.models import Sequential

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

EPOCHS=2
BATCH_SIZE = 1000
NUM_CLASSES=10

x_train=x_train.astype("float32")/255
x_test=x_test.astype("float32")/255
x_train=np.expand_dims(x_train, -1)
x_test=np.expand_dims(x_test, -1)
y_train=keras.utils.to_categorical(y_train,NUM_CLASSES)
y_test=keras.utils.to_categorical(y_test,NUM_CLASSES)

model=Sequential()

model.add(keras.Input(shape=(28,28,1))))
model.add(Conv2D(32, kernel_size=(3,3), activation="relu"))
model.add(Conv2D(64,(3,3), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2))))
model.add (Dropout (0.25))
model.add(Flatten())
model.add(Dense(128, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(NUM_CLASSES, activation="softmax"))

model.compile(optimizer=keras.optimizers.Adadelta(),
            loss=keras.losses.categorical_crossentropy,
            metrics=["accuracy"])

fit_record=model.fit(x_train,y_train,batch_size=BATCH_SIZE,epochs=EPOCHS, verbose=1,validation_data=(x_test,y_test))

model.save("keras-mnist-model.h5")

2022-09-30 16:24

If you have any answers or tips

Popular Tags

python x 4647

android x 1593

java x 1494

javascript x 1427

c x 927

c++ x 878

ruby-on-rails x 696

php x 692

python3 x 685

html x 656