Last answered:

01 Feb 2022

Posted on:

21 Aug 2021

0

Resolved: error in saving a cnn model

model = tf.keras.models.Sequential()
model.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu', input_shape=[256,256,3]))
model.add(tf.keras.layers.MaxPool2D(pool_size = (2,2)))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense( units=128,activation='relu'))
model.add(tf.keras.layers.Dense(4, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

history = model.fit(train_gen,
          epochs=20,
          verbose=1
)

model.save("rock-paper-scissors-model.h5")

AND IT IS SHOWING THIS ERROR

NotImplementedError: Layer ModuleWrapper has arguments in `__init__` and therefore must override `get_config`.
1 answers ( 1 marked as helpful)
Instructor
Posted on:

01 Feb 2022

0

Hi,
This error might be caused because your convolutional layer is Conv2D, instead of tf.keras.layers.Conv2D
Mixing imports between keras and tf.keras can also lead to this error
Hope this helps
Nest,
365 Team

Submit an answer