TypeError: Could not locate class 'Sequential'

[keveinliu]

Greetings,

Thanks for sharing!
I'm using this repo, and I got the following error:

TypeError: Could not locate class 'Sequential'. Make sure custom classes are decorated with `@keras.saving.register_keras_serializable()`. Full object config: {'class_name': 'Sequential', 'config': {'name': 'sequential', 'layers': [{'class_name': 'Conv2D', 'config': {'name': 'conv2d', 'trainable': True, 'batch_input_shape': [None, 48, 48, 1], 'dtype': 'float32', 'filters': 64, 'kernel_size': [3, 3], 'strides': [1, 1], 'padding': 'same', 'data_format': 'channels_last', 'dilation_rate': [1, 1], 'activation': 'linear', 'use_bias': True, 'kernel_initializer': {'class_name': 'GlorotUniform', 'config': {'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'kernel_regularizer': None, 'bias_regularizer': None, 'activity_regularizer': None, 'kernel_constraint': None, 'bias_constraint': None}}, {'class_name': 'BatchNormalization', 'config': {'name': 'batch_normalization', 'trainable': True, 'dtype': 'float32', 'axis': [3], 'momentum
...omitted....

And my tf version is tensorflow-2.16.1.
Is the version incompatible with your code?
Thank you!

[dipsikhade]

Hey!

The tensorflow version which was used to train the model is 2.10 .0, ever since 2.16 was introduced , tensorflow uses keras 3 instead of keras 2. To check the differences between them, you can look through this link!

If you want the code to work, you will need to retrain the model with the current keras version. Hope this helps!